diff options
Diffstat (limited to 'kernel')
163 files changed, 13947 insertions, 3570 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index f85ae5dfa474..04bc07c2b42a 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -41,6 +41,7 @@ obj-y += printk/ obj-y += irq/ obj-y += rcu/ obj-y += livepatch/ +obj-y += dma/ obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o obj-$(CONFIG_FREEZER) += freezer.o @@ -112,7 +113,9 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o -obj-$(CONFIG_HAS_IOMEM) += memremap.o +obj-$(CONFIG_HAS_IOMEM) += iomem.o +obj-$(CONFIG_ZONE_DEVICE) += memremap.o +obj-$(CONFIG_RSEQ) += rseq.o $(obj)/configs.o: $(obj)/config_data.h diff --git a/kernel/audit.c b/kernel/audit.c index 670665c6e2a6..2a8058764aa6 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -83,9 +83,6 @@ #define AUDIT_INITIALIZED 1 static int audit_initialized; -#define AUDIT_OFF 0 -#define AUDIT_ON 1 -#define AUDIT_LOCKED 2 u32 audit_enabled = AUDIT_OFF; bool audit_ever_enabled = !!AUDIT_OFF; @@ -1099,8 +1096,7 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature if (audit_enabled == AUDIT_OFF) return; - - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE); + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_FEATURE_CHANGE); if (!ab) return; audit_log_task_info(ab, current); @@ -1725,7 +1721,7 @@ static inline void audit_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial) { if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { - *t = current_kernel_time64(); + ktime_get_coarse_real_ts64(t); *serial = audit_serial(); } } @@ -1755,7 +1751,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, if (audit_initialized != AUDIT_INITIALIZED) return NULL; - if (unlikely(!audit_filter(type, AUDIT_FILTER_TYPE))) + if (unlikely(!audit_filter(type, AUDIT_FILTER_EXCLUDE))) return NULL; /* NOTE: don't ever fail/sleep on these two conditions: @@ -2317,8 +2313,7 @@ void audit_log_link_denied(const char *operation) return; /* Generate AUDIT_ANOM_LINK with subject, operation, outcome. */ - ab = audit_log_start(current->audit_context, GFP_KERNEL, - AUDIT_ANOM_LINK); + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_ANOM_LINK); if (!ab) return; audit_log_format(ab, "op=%s", operation); diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 52f368b6561e..fba78047fb37 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -109,7 +109,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa audit_update_mark(audit_mark, dentry->d_inode); audit_mark->rule = krule; - ret = fsnotify_add_mark(&audit_mark->mark, inode, NULL, true); + ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true); if (ret < 0) { fsnotify_put_mark(&audit_mark->mark); audit_mark = ERR_PTR(ret); @@ -165,12 +165,11 @@ static void audit_autoremove_mark_rule(struct audit_fsnotify_mark *audit_mark) /* Update mark data in audit rules based on fsnotify events. */ static int audit_mark_handle_event(struct fsnotify_group *group, struct inode *to_tell, - struct fsnotify_mark *inode_mark, - struct fsnotify_mark *vfsmount_mark, u32 mask, const void *data, int data_type, const unsigned char *dname, u32 cookie, struct fsnotify_iter_info *iter_info) { + struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); struct audit_fsnotify_mark *audit_mark; const struct inode *inode = NULL; diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 67e6956c0b61..9f6eaeb6919f 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -288,8 +288,8 @@ static void untag_chunk(struct node *p) if (!new) goto Fallback; - if (fsnotify_add_mark_locked(&new->mark, entry->connector->inode, - NULL, 1)) { + if (fsnotify_add_inode_mark_locked(&new->mark, entry->connector->inode, + 1)) { fsnotify_put_mark(&new->mark); goto Fallback; } @@ -354,7 +354,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree) return -ENOMEM; entry = &chunk->mark; - if (fsnotify_add_mark(entry, inode, NULL, 0)) { + if (fsnotify_add_inode_mark(entry, inode, 0)) { fsnotify_put_mark(entry); return -ENOSPC; } @@ -434,8 +434,8 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) return -ENOENT; } - if (fsnotify_add_mark_locked(chunk_entry, - old_entry->connector->inode, NULL, 1)) { + if (fsnotify_add_inode_mark_locked(chunk_entry, + old_entry->connector->inode, 1)) { spin_unlock(&old_entry->lock); mutex_unlock(&old_entry->group->mark_mutex); fsnotify_put_mark(chunk_entry); @@ -497,6 +497,8 @@ static void audit_tree_log_remove_rule(struct audit_krule *rule) { struct audit_buffer *ab; + if (!audit_enabled) + return; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (unlikely(!ab)) return; @@ -989,8 +991,6 @@ static void evict_chunk(struct audit_chunk *chunk) static int audit_tree_handle_event(struct fsnotify_group *group, struct inode *to_tell, - struct fsnotify_mark *inode_mark, - struct fsnotify_mark *vfsmount_mark, u32 mask, const void *data, int data_type, const unsigned char *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 9eb8b3511636..787c7afdf829 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -160,7 +160,7 @@ static struct audit_parent *audit_init_parent(struct path *path) fsnotify_init_mark(&parent->mark, audit_watch_group); parent->mark.mask = AUDIT_FS_WATCH; - ret = fsnotify_add_mark(&parent->mark, inode, NULL, 0); + ret = fsnotify_add_inode_mark(&parent->mark, inode, 0); if (ret < 0) { audit_free_parent(parent); return ERR_PTR(ret); @@ -238,20 +238,21 @@ out: static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watch *w, char *op) { - if (audit_enabled) { - struct audit_buffer *ab; - ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE); - if (unlikely(!ab)) - return; - audit_log_format(ab, "auid=%u ses=%u op=%s", - from_kuid(&init_user_ns, audit_get_loginuid(current)), - audit_get_sessionid(current), op); - audit_log_format(ab, " path="); - audit_log_untrustedstring(ab, w->path); - audit_log_key(ab, r->filterkey); - audit_log_format(ab, " list=%d res=1", r->listnr); - audit_log_end(ab); - } + struct audit_buffer *ab; + + if (!audit_enabled) + return; + ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE); + if (!ab) + return; + audit_log_format(ab, "auid=%u ses=%u op=%s", + from_kuid(&init_user_ns, audit_get_loginuid(current)), + audit_get_sessionid(current), op); + audit_log_format(ab, " path="); + audit_log_untrustedstring(ab, w->path); + audit_log_key(ab, r->filterkey); + audit_log_format(ab, " list=%d res=1", r->listnr); + audit_log_end(ab); } /* Update inode info in audit rules based on filesystem event. */ @@ -274,7 +275,7 @@ static void audit_update_watch(struct audit_parent *parent, /* If the update involves invalidating rules, do the inode-based * filtering now, so we don't omit records. */ if (invalidating && !audit_dummy_context()) - audit_filter_inodes(current, current->audit_context); + audit_filter_inodes(current, audit_context()); /* updating ino will likely change which audit_hash_list we * are on so we need a new watch for the new list */ @@ -419,6 +420,13 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) struct path parent_path; int h, ret = 0; + /* + * When we will be calling audit_add_to_parent, krule->watch might have + * been updated and watch might have been freed. + * So we need to keep a reference of watch. + */ + audit_get_watch(watch); + mutex_unlock(&audit_filter_mutex); /* Avoid calling path_lookup under audit_filter_mutex. */ @@ -427,8 +435,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) /* caller expects mutex locked */ mutex_lock(&audit_filter_mutex); - if (ret) + if (ret) { + audit_put_watch(watch); return ret; + } /* either find an old parent or attach a new one */ parent = audit_find_parent(d_backing_inode(parent_path.dentry)); @@ -446,6 +456,7 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) *list = &audit_inode_hash[h]; error: path_put(&parent_path); + audit_put_watch(watch); return ret; } @@ -472,12 +483,11 @@ void audit_remove_watch_rule(struct audit_krule *krule) /* Update watch data in audit rules based on fsnotify events. */ static int audit_watch_handle_event(struct fsnotify_group *group, struct inode *to_tell, - struct fsnotify_mark *inode_mark, - struct fsnotify_mark *vfsmount_mark, u32 mask, const void *data, int data_type, const unsigned char *dname, u32 cookie, struct fsnotify_iter_info *iter_info) { + struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); const struct inode *inode; struct audit_parent *parent; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index d7a807e81451..bf309f2592c4 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -264,7 +264,7 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data * case AUDIT_FILTER_TASK: #endif case AUDIT_FILTER_USER: - case AUDIT_FILTER_TYPE: + case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: ; } @@ -337,7 +337,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) { switch(f->type) { case AUDIT_MSGTYPE: - if (entry->rule.listnr != AUDIT_FILTER_TYPE && + if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE && entry->rule.listnr != AUDIT_FILTER_USER) return -EINVAL; break; @@ -426,9 +426,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) return -EINVAL; break; case AUDIT_EXE: - if (f->op != Audit_equal) - return -EINVAL; - if (entry->rule.listnr != AUDIT_FILTER_EXIT) + if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; break; } @@ -931,7 +929,7 @@ static inline int audit_add_rule(struct audit_entry *entry) /* If any of these, don't count towards total */ switch(entry->rule.listnr) { case AUDIT_FILTER_USER: - case AUDIT_FILTER_TYPE: + case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } @@ -1013,7 +1011,7 @@ int audit_del_rule(struct audit_entry *entry) /* If any of these, don't count towards total */ switch(entry->rule.listnr) { case AUDIT_FILTER_USER: - case AUDIT_FILTER_TYPE: + case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } @@ -1089,8 +1087,6 @@ static void audit_list_rules(int seq, struct sk_buff_head *q) static void audit_log_rule_change(char *action, struct audit_krule *rule, int res) { struct audit_buffer *ab; - uid_t loginuid = from_kuid(&init_user_ns, audit_get_loginuid(current)); - unsigned int sessionid = audit_get_sessionid(current); if (!audit_enabled) return; @@ -1098,7 +1094,7 @@ static void audit_log_rule_change(char *action, struct audit_krule *rule, int re ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (!ab) return; - audit_log_format(ab, "auid=%u ses=%u" ,loginuid, sessionid); + audit_log_session_info(ab); audit_log_task_context(ab); audit_log_format(ab, " op=%s", action); audit_log_key(ab, rule->filterkey); @@ -1362,6 +1358,11 @@ int audit_filter(int msgtype, unsigned int listtype) f->type, f->op, f->lsm_rule, NULL); } break; + case AUDIT_EXE: + result = audit_exe_compare(current, e->rule.exe); + if (f->op == Audit_not_equal) + result = !result; + break; default: goto unlock_and_return; } @@ -1371,7 +1372,7 @@ int audit_filter(int msgtype, unsigned int listtype) break; } if (result > 0) { - if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_TYPE) + if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE) ret = 0; break; } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 4e0a4ac803db..b2d1f043f17f 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -374,7 +374,7 @@ static int audit_field_compare(struct task_struct *tsk, case AUDIT_COMPARE_EGID_TO_OBJ_GID: return audit_compare_gid(cred->egid, name, f, ctx); case AUDIT_COMPARE_AUID_TO_OBJ_UID: - return audit_compare_uid(tsk->loginuid, name, f, ctx); + return audit_compare_uid(audit_get_loginuid(tsk), name, f, ctx); case AUDIT_COMPARE_SUID_TO_OBJ_UID: return audit_compare_uid(cred->suid, name, f, ctx); case AUDIT_COMPARE_SGID_TO_OBJ_GID: @@ -385,7 +385,8 @@ static int audit_field_compare(struct task_struct *tsk, return audit_compare_gid(cred->fsgid, name, f, ctx); /* uid comparisons */ case AUDIT_COMPARE_UID_TO_AUID: - return audit_uid_comparator(cred->uid, f->op, tsk->loginuid); + return audit_uid_comparator(cred->uid, f->op, + audit_get_loginuid(tsk)); case AUDIT_COMPARE_UID_TO_EUID: return audit_uid_comparator(cred->uid, f->op, cred->euid); case AUDIT_COMPARE_UID_TO_SUID: @@ -394,11 +395,14 @@ static int audit_field_compare(struct task_struct *tsk, return audit_uid_comparator(cred->uid, f->op, cred->fsuid); /* auid comparisons */ case AUDIT_COMPARE_AUID_TO_EUID: - return audit_uid_comparator(tsk->loginuid, f->op, cred->euid); + return audit_uid_comparator(audit_get_loginuid(tsk), f->op, + cred->euid); case AUDIT_COMPARE_AUID_TO_SUID: - return audit_uid_comparator(tsk->loginuid, f->op, cred->suid); + return audit_uid_comparator(audit_get_loginuid(tsk), f->op, + cred->suid); case AUDIT_COMPARE_AUID_TO_FSUID: - return audit_uid_comparator(tsk->loginuid, f->op, cred->fsuid); + return audit_uid_comparator(audit_get_loginuid(tsk), f->op, + cred->fsuid); /* euid comparisons */ case AUDIT_COMPARE_EUID_TO_SUID: return audit_uid_comparator(cred->euid, f->op, cred->suid); @@ -471,6 +475,8 @@ static int audit_filter_rules(struct task_struct *tsk, break; case AUDIT_EXE: result = audit_exe_compare(tsk, rule->exe); + if (f->op == Audit_not_equal) + result = !result; break; case AUDIT_UID: result = audit_uid_comparator(cred->uid, f->op, f->uid); @@ -488,20 +494,20 @@ static int audit_filter_rules(struct task_struct *tsk, result = audit_gid_comparator(cred->gid, f->op, f->gid); if (f->op == Audit_equal) { if (!result) - result = in_group_p(f->gid); + result = groups_search(cred->group_info, f->gid); } else if (f->op == Audit_not_equal) { if (result) - result = !in_group_p(f->gid); + result = !groups_search(cred->group_info, f->gid); } break; case AUDIT_EGID: result = audit_gid_comparator(cred->egid, f->op, f->gid); if (f->op == Audit_equal) { if (!result) - result = in_egroup_p(f->gid); + result = groups_search(cred->group_info, f->gid); } else if (f->op == Audit_not_equal) { if (result) - result = !in_egroup_p(f->gid); + result = !groups_search(cred->group_info, f->gid); } break; case AUDIT_SGID: @@ -511,7 +517,7 @@ static int audit_filter_rules(struct task_struct *tsk, result = audit_gid_comparator(cred->fsgid, f->op, f->gid); break; case AUDIT_SESSIONID: - sessionid = audit_get_sessionid(current); + sessionid = audit_get_sessionid(tsk); result = audit_comparator(sessionid, f->op, f->val); break; case AUDIT_PERS: @@ -609,7 +615,8 @@ static int audit_filter_rules(struct task_struct *tsk, result = match_tree_refs(ctx, rule->tree); break; case AUDIT_LOGINUID: - result = audit_uid_comparator(tsk->loginuid, f->op, f->uid); + result = audit_uid_comparator(audit_get_loginuid(tsk), + f->op, f->uid); break; case AUDIT_LOGINUID_SET: result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val); @@ -863,7 +870,7 @@ static inline struct audit_context *audit_take_context(struct task_struct *tsk, audit_filter_inodes(tsk, context); } - tsk->audit_context = NULL; + audit_set_context(tsk, NULL); return context; } @@ -950,7 +957,7 @@ int audit_alloc(struct task_struct *tsk) } context->filterkey = key; - tsk->audit_context = context; + audit_set_context(tsk, context); set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT); return 0; } @@ -1272,8 +1279,12 @@ static void show_special(struct audit_context *context, int *call_panic) break; case AUDIT_KERN_MODULE: audit_log_format(ab, "name="); - audit_log_untrustedstring(ab, context->module.name); - kfree(context->module.name); + if (context->module.name) { + audit_log_untrustedstring(ab, context->module.name); + kfree(context->module.name); + } else + audit_log_format(ab, "(null)"); + break; } audit_log_end(ab); @@ -1507,8 +1518,7 @@ void __audit_free(struct task_struct *tsk) void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, unsigned long a3, unsigned long a4) { - struct task_struct *tsk = current; - struct audit_context *context = tsk->audit_context; + struct audit_context *context = audit_context(); enum audit_state state; if (!audit_enabled || !context) @@ -1523,7 +1533,7 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, context->dummy = !audit_n_rules; if (!context->dummy && state == AUDIT_BUILD_CONTEXT) { context->prio = 0; - if (auditd_test_task(tsk)) + if (auditd_test_task(current)) return; } @@ -1534,10 +1544,10 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, context->argv[2] = a3; context->argv[3] = a4; context->serial = 0; - context->ctime = current_kernel_time64(); context->in_syscall = 1; context->current_state = state; context->ppid = 0; + ktime_get_coarse_real_ts64(&context->ctime); } /** @@ -1553,7 +1563,6 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, */ void __audit_syscall_exit(int success, long return_code) { - struct task_struct *tsk = current; struct audit_context *context; if (success) @@ -1561,12 +1570,12 @@ void __audit_syscall_exit(int success, long return_code) else success = AUDITSC_FAILURE; - context = audit_take_context(tsk, success, return_code); + context = audit_take_context(current, success, return_code); if (!context) return; if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT) - audit_log_exit(context, tsk); + audit_log_exit(context, current); context->in_syscall = 0; context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; @@ -1588,7 +1597,7 @@ void __audit_syscall_exit(int success, long return_code) kfree(context->filterkey); context->filterkey = NULL; } - tsk->audit_context = context; + audit_set_context(current, context); } static inline void handle_one(const struct inode *inode) @@ -1600,7 +1609,7 @@ static inline void handle_one(const struct inode *inode) int count; if (likely(!inode->i_fsnotify_marks)) return; - context = current->audit_context; + context = audit_context(); p = context->trees; count = context->tree_count; rcu_read_lock(); @@ -1631,7 +1640,7 @@ static void handle_path(const struct dentry *dentry) unsigned long seq; int count; - context = current->audit_context; + context = audit_context(); p = context->trees; count = context->tree_count; retry: @@ -1713,7 +1722,7 @@ static struct audit_names *audit_alloc_name(struct audit_context *context, struct filename * __audit_reusename(const __user char *uptr) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct audit_names *n; list_for_each_entry(n, &context->names_list, list) { @@ -1736,7 +1745,7 @@ __audit_reusename(const __user char *uptr) */ void __audit_getname(struct filename *name) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct audit_names *n; if (!context->in_syscall) @@ -1764,7 +1773,7 @@ void __audit_getname(struct filename *name) void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct inode *inode = d_backing_inode(dentry); struct audit_names *n; bool parent = flags & AUDIT_INODE_PARENT; @@ -1863,7 +1872,7 @@ void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct inode *inode = d_backing_inode(dentry); const char *dname = dentry->d_name.name; struct audit_names *n, *found_parent = NULL, *found_child = NULL; @@ -2048,7 +2057,7 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, int audit_set_loginuid(kuid_t loginuid) { struct task_struct *task = current; - unsigned int oldsessionid, sessionid = (unsigned int)-1; + unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET; kuid_t oldloginuid; int rc; @@ -2062,7 +2071,7 @@ int audit_set_loginuid(kuid_t loginuid) /* are we setting or clearing? */ if (uid_valid(loginuid)) { sessionid = (unsigned int)atomic_inc_return(&session_id); - if (unlikely(sessionid == (unsigned int)-1)) + if (unlikely(sessionid == AUDIT_SID_UNSET)) sessionid = (unsigned int)atomic_inc_return(&session_id); } @@ -2082,7 +2091,7 @@ out: */ void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); if (attr) memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr)); @@ -2106,7 +2115,7 @@ void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct timespec64 *p = &context->mq_sendrecv.abs_timeout; if (abs_timeout) @@ -2130,7 +2139,7 @@ void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); if (notification) context->mq_notify.sigev_signo = notification->sigev_signo; @@ -2149,7 +2158,7 @@ void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) */ void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->mq_getsetattr.mqdes = mqdes; context->mq_getsetattr.mqstat = *mqstat; context->type = AUDIT_MQ_GETSETATTR; @@ -2162,7 +2171,7 @@ void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) */ void __audit_ipc_obj(struct kern_ipc_perm *ipcp) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->ipc.uid = ipcp->uid; context->ipc.gid = ipcp->gid; context->ipc.mode = ipcp->mode; @@ -2182,7 +2191,7 @@ void __audit_ipc_obj(struct kern_ipc_perm *ipcp) */ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->ipc.qbytes = qbytes; context->ipc.perm_uid = uid; @@ -2193,7 +2202,7 @@ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mo void __audit_bprm(struct linux_binprm *bprm) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->type = AUDIT_EXECVE; context->execve.argc = bprm->argc; @@ -2208,7 +2217,7 @@ void __audit_bprm(struct linux_binprm *bprm) */ int __audit_socketcall(int nargs, unsigned long *args) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); if (nargs <= 0 || nargs > AUDITSC_ARGS || !args) return -EINVAL; @@ -2226,7 +2235,7 @@ int __audit_socketcall(int nargs, unsigned long *args) */ void __audit_fd_pair(int fd1, int fd2) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->fds[0] = fd1; context->fds[1] = fd2; } @@ -2240,7 +2249,7 @@ void __audit_fd_pair(int fd1, int fd2) */ int __audit_sockaddr(int len, void *a) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); if (!context->sockaddr) { void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL); @@ -2256,7 +2265,7 @@ int __audit_sockaddr(int len, void *a) void __audit_ptrace(struct task_struct *t) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->target_pid = task_tgid_nr(t); context->target_auid = audit_get_loginuid(t); @@ -2277,19 +2286,19 @@ void __audit_ptrace(struct task_struct *t) int audit_signal_info(int sig, struct task_struct *t) { struct audit_aux_data_pids *axp; - struct task_struct *tsk = current; - struct audit_context *ctx = tsk->audit_context; - kuid_t uid = current_uid(), t_uid = task_uid(t); + struct audit_context *ctx = audit_context(); + kuid_t uid = current_uid(), auid, t_uid = task_uid(t); if (auditd_test_task(t) && (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2)) { - audit_sig_pid = task_tgid_nr(tsk); - if (uid_valid(tsk->loginuid)) - audit_sig_uid = tsk->loginuid; + audit_sig_pid = task_tgid_nr(current); + auid = audit_get_loginuid(current); + if (uid_valid(auid)) + audit_sig_uid = auid; else audit_sig_uid = uid; - security_task_getsecid(tsk, &audit_sig_sid); + security_task_getsecid(current, &audit_sig_sid); } if (!audit_signals || audit_dummy_context()) @@ -2345,7 +2354,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { struct audit_aux_data_bprm_fcaps *ax; - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); struct cpu_vfs_cap_data vcaps; ax = kmalloc(sizeof(*ax), GFP_KERNEL); @@ -2385,7 +2394,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, */ void __audit_log_capset(const struct cred *new, const struct cred *old) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->capset.pid = task_tgid_nr(current); context->capset.cap.effective = new->cap_effective; context->capset.cap.inheritable = new->cap_effective; @@ -2396,7 +2405,7 @@ void __audit_log_capset(const struct cred *new, const struct cred *old) void __audit_mmap_fd(int fd, int flags) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); context->mmap.fd = fd; context->mmap.flags = flags; context->type = AUDIT_MMAP; @@ -2404,16 +2413,17 @@ void __audit_mmap_fd(int fd, int flags) void __audit_log_kern_module(char *name) { - struct audit_context *context = current->audit_context; + struct audit_context *context = audit_context(); - context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL); - strcpy(context->module.name, name); + context->module.name = kstrdup(name, GFP_KERNEL); + if (!context->module.name) + audit_log_lost("out of memory in __audit_log_kern_module"); context->type = AUDIT_KERN_MODULE; } void __audit_fanotify(unsigned int response) { - audit_log(current->audit_context, GFP_KERNEL, + audit_log(audit_context(), GFP_KERNEL, AUDIT_FANOTIFY, "resp=%u", response); } @@ -2456,7 +2466,7 @@ void audit_core_dumps(long signr) if (signr == SIGQUIT) /* don't care for those */ return; - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_ANOM_ABEND); if (unlikely(!ab)) return; audit_log_task(ab); @@ -2464,11 +2474,23 @@ void audit_core_dumps(long signr) audit_log_end(ab); } -void __audit_seccomp(unsigned long syscall, long signr, int code) +/** + * audit_seccomp - record information about a seccomp action + * @syscall: syscall number + * @signr: signal value + * @code: the seccomp action + * + * Record the information associated with a seccomp action. Event filtering for + * seccomp actions that are not to be logged is done in seccomp_log(). + * Therefore, this function forces auditing independent of the audit_enabled + * and dummy context state because seccomp actions should be logged even when + * audit is not in use. + */ +void audit_seccomp(unsigned long syscall, long signr, int code) { struct audit_buffer *ab; - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP); + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_SECCOMP); if (unlikely(!ab)) return; audit_log_task(ab); @@ -2478,9 +2500,29 @@ void __audit_seccomp(unsigned long syscall, long signr, int code) audit_log_end(ab); } +void audit_seccomp_actions_logged(const char *names, const char *old_names, + int res) +{ + struct audit_buffer *ab; + + if (!audit_enabled) + return; + + ab = audit_log_start(audit_context(), GFP_KERNEL, + AUDIT_CONFIG_CHANGE); + if (unlikely(!ab)) + return; + + audit_log_format(ab, "op=seccomp-logging"); + audit_log_format(ab, " actions=%s", names); + audit_log_format(ab, " old-actions=%s", old_names); + audit_log_format(ab, " res=%d", res); + audit_log_end(ab); +} + struct list_head *audit_killed_trees(void) { - struct audit_context *ctx = current->audit_context; + struct audit_context *ctx = audit_context(); if (likely(!ctx || !ctx->in_syscall)) return NULL; return &ctx->killed_trees; diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index a713fd23ec88..f27f5496d6fe 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -4,9 +4,13 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o +obj-$(CONFIG_BPF_SYSCALL) += btf.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o +ifeq ($(CONFIG_XDP_SOCKETS),y) +obj-$(CONFIG_BPF_SYSCALL) += xskmap.o +endif obj-$(CONFIG_BPF_SYSCALL) += offload.o ifeq ($(CONFIG_STREAM_PARSER),y) ifeq ($(CONFIG_INET),y) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 027107f4be53..2aa55d030c77 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -11,11 +11,13 @@ * General Public License for more details. */ #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/filter.h> #include <linux/perf_event.h> +#include <uapi/linux/btf.h> #include "map_in_map.h" @@ -336,6 +338,52 @@ static void array_map_free(struct bpf_map *map) bpf_map_area_free(array); } +static void array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + void *value; + + rcu_read_lock(); + + value = array_map_lookup_elem(map, key); + if (!value) { + rcu_read_unlock(); + return; + } + + seq_printf(m, "%u: ", *(u32 *)key); + btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); + seq_puts(m, "\n"); + + rcu_read_unlock(); +} + +static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf, + u32 btf_key_id, u32 btf_value_id) +{ + const struct btf_type *key_type, *value_type; + u32 key_size, value_size; + u32 int_data; + + key_type = btf_type_id_size(btf, &btf_key_id, &key_size); + if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; + + int_data = *(u32 *)(key_type + 1); + /* bpf array can only take a u32 key. This check makes + * sure that the btf matches the attr used during map_create. + */ + if (BTF_INT_BITS(int_data) != 32 || key_size != 4 || + BTF_INT_OFFSET(int_data)) + return -EINVAL; + + value_type = btf_type_id_size(btf, &btf_value_id, &value_size); + if (!value_type || value_size != map->value_size) + return -EINVAL; + + return 0; +} + const struct bpf_map_ops array_map_ops = { .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, @@ -345,6 +393,8 @@ const struct bpf_map_ops array_map_ops = { .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, .map_gen_lookup = array_map_gen_lookup, + .map_seq_show_elem = array_map_seq_show_elem, + .map_check_btf = array_map_check_btf, }; const struct bpf_map_ops percpu_array_map_ops = { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c new file mode 100644 index 000000000000..2590700237c1 --- /dev/null +++ b/kernel/bpf/btf.c @@ -0,0 +1,2360 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#include <uapi/linux/btf.h> +#include <uapi/linux/types.h> +#include <linux/seq_file.h> +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/anon_inodes.h> +#include <linux/file.h> +#include <linux/uaccess.h> +#include <linux/kernel.h> +#include <linux/idr.h> +#include <linux/sort.h> +#include <linux/bpf_verifier.h> +#include <linux/btf.h> + +/* BTF (BPF Type Format) is the meta data format which describes + * the data types of BPF program/map. Hence, it basically focus + * on the C programming language which the modern BPF is primary + * using. + * + * ELF Section: + * ~~~~~~~~~~~ + * The BTF data is stored under the ".BTF" ELF section + * + * struct btf_type: + * ~~~~~~~~~~~~~~~ + * Each 'struct btf_type' object describes a C data type. + * Depending on the type it is describing, a 'struct btf_type' + * object may be followed by more data. F.e. + * To describe an array, 'struct btf_type' is followed by + * 'struct btf_array'. + * + * 'struct btf_type' and any extra data following it are + * 4 bytes aligned. + * + * Type section: + * ~~~~~~~~~~~~~ + * The BTF type section contains a list of 'struct btf_type' objects. + * Each one describes a C type. Recall from the above section + * that a 'struct btf_type' object could be immediately followed by extra + * data in order to desribe some particular C types. + * + * type_id: + * ~~~~~~~ + * Each btf_type object is identified by a type_id. The type_id + * is implicitly implied by the location of the btf_type object in + * the BTF type section. The first one has type_id 1. The second + * one has type_id 2...etc. Hence, an earlier btf_type has + * a smaller type_id. + * + * A btf_type object may refer to another btf_type object by using + * type_id (i.e. the "type" in the "struct btf_type"). + * + * NOTE that we cannot assume any reference-order. + * A btf_type object can refer to an earlier btf_type object + * but it can also refer to a later btf_type object. + * + * For example, to describe "const void *". A btf_type + * object describing "const" may refer to another btf_type + * object describing "void *". This type-reference is done + * by specifying type_id: + * + * [1] CONST (anon) type_id=2 + * [2] PTR (anon) type_id=0 + * + * The above is the btf_verifier debug log: + * - Each line started with "[?]" is a btf_type object + * - [?] is the type_id of the btf_type object. + * - CONST/PTR is the BTF_KIND_XXX + * - "(anon)" is the name of the type. It just + * happens that CONST and PTR has no name. + * - type_id=XXX is the 'u32 type' in btf_type + * + * NOTE: "void" has type_id 0 + * + * String section: + * ~~~~~~~~~~~~~~ + * The BTF string section contains the names used by the type section. + * Each string is referred by an "offset" from the beginning of the + * string section. + * + * Each string is '\0' terminated. + * + * The first character in the string section must be '\0' + * which is used to mean 'anonymous'. Some btf_type may not + * have a name. + */ + +/* BTF verification: + * + * To verify BTF data, two passes are needed. + * + * Pass #1 + * ~~~~~~~ + * The first pass is to collect all btf_type objects to + * an array: "btf->types". + * + * Depending on the C type that a btf_type is describing, + * a btf_type may be followed by extra data. We don't know + * how many btf_type is there, and more importantly we don't + * know where each btf_type is located in the type section. + * + * Without knowing the location of each type_id, most verifications + * cannot be done. e.g. an earlier btf_type may refer to a later + * btf_type (recall the "const void *" above), so we cannot + * check this type-reference in the first pass. + * + * In the first pass, it still does some verifications (e.g. + * checking the name is a valid offset to the string section). + * + * Pass #2 + * ~~~~~~~ + * The main focus is to resolve a btf_type that is referring + * to another type. + * + * We have to ensure the referring type: + * 1) does exist in the BTF (i.e. in btf->types[]) + * 2) does not cause a loop: + * struct A { + * struct B b; + * }; + * + * struct B { + * struct A a; + * }; + * + * btf_type_needs_resolve() decides if a btf_type needs + * to be resolved. + * + * The needs_resolve type implements the "resolve()" ops which + * essentially does a DFS and detects backedge. + * + * During resolve (or DFS), different C types have different + * "RESOLVED" conditions. + * + * When resolving a BTF_KIND_STRUCT, we need to resolve all its + * members because a member is always referring to another + * type. A struct's member can be treated as "RESOLVED" if + * it is referring to a BTF_KIND_PTR. Otherwise, the + * following valid C struct would be rejected: + * + * struct A { + * int m; + * struct A *a; + * }; + * + * When resolving a BTF_KIND_PTR, it needs to keep resolving if + * it is referring to another BTF_KIND_PTR. Otherwise, we cannot + * detect a pointer loop, e.g.: + * BTF_KIND_CONST -> BTF_KIND_PTR -> BTF_KIND_CONST -> BTF_KIND_PTR + + * ^ | + * +-----------------------------------------+ + * + */ + +#define BITS_PER_U64 (sizeof(u64) * BITS_PER_BYTE) +#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1) +#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK) +#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3) +#define BITS_ROUNDUP_BYTES(bits) \ + (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) + +#define BTF_INFO_MASK 0x0f00ffff +#define BTF_INT_MASK 0x0fffffff +#define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE) +#define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET) + +/* 16MB for 64k structs and each has 16 members and + * a few MB spaces for the string section. + * The hard limit is S32_MAX. + */ +#define BTF_MAX_SIZE (16 * 1024 * 1024) + +#define for_each_member(i, struct_type, member) \ + for (i = 0, member = btf_type_member(struct_type); \ + i < btf_type_vlen(struct_type); \ + i++, member++) + +#define for_each_member_from(i, from, struct_type, member) \ + for (i = from, member = btf_type_member(struct_type) + from; \ + i < btf_type_vlen(struct_type); \ + i++, member++) + +static DEFINE_IDR(btf_idr); +static DEFINE_SPINLOCK(btf_idr_lock); + +struct btf { + void *data; + struct btf_type **types; + u32 *resolved_ids; + u32 *resolved_sizes; + const char *strings; + void *nohdr_data; + struct btf_header hdr; + u32 nr_types; + u32 types_size; + u32 data_size; + refcount_t refcnt; + u32 id; + struct rcu_head rcu; +}; + +enum verifier_phase { + CHECK_META, + CHECK_TYPE, +}; + +struct resolve_vertex { + const struct btf_type *t; + u32 type_id; + u16 next_member; +}; + +enum visit_state { + NOT_VISITED, + VISITED, + RESOLVED, +}; + +enum resolve_mode { + RESOLVE_TBD, /* To Be Determined */ + RESOLVE_PTR, /* Resolving for Pointer */ + RESOLVE_STRUCT_OR_ARRAY, /* Resolving for struct/union + * or array + */ +}; + +#define MAX_RESOLVE_DEPTH 32 + +struct btf_sec_info { + u32 off; + u32 len; +}; + +struct btf_verifier_env { + struct btf *btf; + u8 *visit_states; + struct resolve_vertex stack[MAX_RESOLVE_DEPTH]; + struct bpf_verifier_log log; + u32 log_type_id; + u32 top_stack; + enum verifier_phase phase; + enum resolve_mode resolve_mode; +}; + +static const char * const btf_kind_str[NR_BTF_KINDS] = { + [BTF_KIND_UNKN] = "UNKNOWN", + [BTF_KIND_INT] = "INT", + [BTF_KIND_PTR] = "PTR", + [BTF_KIND_ARRAY] = "ARRAY", + [BTF_KIND_STRUCT] = "STRUCT", + [BTF_KIND_UNION] = "UNION", + [BTF_KIND_ENUM] = "ENUM", + [BTF_KIND_FWD] = "FWD", + [BTF_KIND_TYPEDEF] = "TYPEDEF", + [BTF_KIND_VOLATILE] = "VOLATILE", + [BTF_KIND_CONST] = "CONST", + [BTF_KIND_RESTRICT] = "RESTRICT", +}; + +struct btf_kind_operations { + s32 (*check_meta)(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left); + int (*resolve)(struct btf_verifier_env *env, + const struct resolve_vertex *v); + int (*check_member)(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type); + void (*log_details)(struct btf_verifier_env *env, + const struct btf_type *t); + void (*seq_show)(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offsets, + struct seq_file *m); +}; + +static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS]; +static struct btf_type btf_void; + +static bool btf_type_is_modifier(const struct btf_type *t) +{ + /* Some of them is not strictly a C modifier + * but they are grouped into the same bucket + * for BTF concern: + * A type (t) that refers to another + * type through t->type AND its size cannot + * be determined without following the t->type. + * + * ptr does not fall into this bucket + * because its size is always sizeof(void *). + */ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return true; + } + + return false; +} + +static bool btf_type_is_void(const struct btf_type *t) +{ + /* void => no type and size info. + * Hence, FWD is also treated as void. + */ + return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + +static bool btf_type_is_void_or_null(const struct btf_type *t) +{ + return !t || btf_type_is_void(t); +} + +/* union is only a special case of struct: + * all its offsetof(member) == 0 + */ +static bool btf_type_is_struct(const struct btf_type *t) +{ + u8 kind = BTF_INFO_KIND(t->info); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static bool btf_type_is_array(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; +} + +static bool btf_type_is_ptr(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; +} + +static bool btf_type_is_int(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_INT; +} + +/* What types need to be resolved? + * + * btf_type_is_modifier() is an obvious one. + * + * btf_type_is_struct() because its member refers to + * another type (through member->type). + + * btf_type_is_array() because its element (array->type) + * refers to another type. Array can be thought of a + * special case of struct while array just has the same + * member-type repeated by array->nelems of times. + */ +static bool btf_type_needs_resolve(const struct btf_type *t) +{ + return btf_type_is_modifier(t) || + btf_type_is_ptr(t) || + btf_type_is_struct(t) || + btf_type_is_array(t); +} + +/* t->size can be used */ +static bool btf_type_has_size(const struct btf_type *t) +{ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + return true; + } + + return false; +} + +static const char *btf_int_encoding_str(u8 encoding) +{ + if (encoding == 0) + return "(none)"; + else if (encoding == BTF_INT_SIGNED) + return "SIGNED"; + else if (encoding == BTF_INT_CHAR) + return "CHAR"; + else if (encoding == BTF_INT_BOOL) + return "BOOL"; + else + return "UNKN"; +} + +static u16 btf_type_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static u32 btf_type_int(const struct btf_type *t) +{ + return *(u32 *)(t + 1); +} + +static const struct btf_array *btf_type_array(const struct btf_type *t) +{ + return (const struct btf_array *)(t + 1); +} + +static const struct btf_member *btf_type_member(const struct btf_type *t) +{ + return (const struct btf_member *)(t + 1); +} + +static const struct btf_enum *btf_type_enum(const struct btf_type *t) +{ + return (const struct btf_enum *)(t + 1); +} + +static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) +{ + return kind_ops[BTF_INFO_KIND(t->info)]; +} + +static bool btf_name_offset_valid(const struct btf *btf, u32 offset) +{ + return BTF_STR_OFFSET_VALID(offset) && + offset < btf->hdr.str_len; +} + +static const char *btf_name_by_offset(const struct btf *btf, u32 offset) +{ + if (!offset) + return "(anon)"; + else if (offset < btf->hdr.str_len) + return &btf->strings[offset]; + else + return "(invalid-name-offset)"; +} + +static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} + +/* + * Regular int is not a bit field and it must be either + * u8/u16/u32/u64. + */ +static bool btf_type_int_is_regular(const struct btf_type *t) +{ + u8 nr_bits, nr_bytes; + u32 int_data; + + int_data = btf_type_int(t); + nr_bits = BTF_INT_BITS(int_data); + nr_bytes = BITS_ROUNDUP_BYTES(nr_bits); + if (BITS_PER_BYTE_MASKED(nr_bits) || + BTF_INT_OFFSET(int_data) || + (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) && + nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) { + return false; + } + + return true; +} + +__printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log, + const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} + +__printf(2, 3) static void btf_verifier_log(struct btf_verifier_env *env, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} + +__printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, + const struct btf_type *t, + bool log_details, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + u8 kind = BTF_INFO_KIND(t->info); + struct btf *btf = env->btf; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + __btf_verifier_log(log, "[%u] %s %s%s", + env->log_type_id, + btf_kind_str[kind], + btf_name_by_offset(btf, t->name_off), + log_details ? " " : ""); + + if (log_details) + btf_type_ops(t)->log_details(env, t); + + if (fmt && *fmt) { + __btf_verifier_log(log, " "); + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); + } + + __btf_verifier_log(log, "\n"); +} + +#define btf_verifier_log_type(env, t, ...) \ + __btf_verifier_log_type((env), (t), true, __VA_ARGS__) +#define btf_verifier_log_basic(env, t, ...) \ + __btf_verifier_log_type((env), (t), false, __VA_ARGS__) + +__printf(4, 5) +static void btf_verifier_log_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + struct btf *btf = env->btf; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + /* The CHECK_META phase already did a btf dump. + * + * If member is logged again, it must hit an error in + * parsing this member. It is useful to print out which + * struct this member belongs to. + */ + if (env->phase != CHECK_META) + btf_verifier_log_type(env, struct_type, NULL); + + __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u", + btf_name_by_offset(btf, member->name_off), + member->type, member->offset); + + if (fmt && *fmt) { + __btf_verifier_log(log, " "); + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); + } + + __btf_verifier_log(log, "\n"); +} + +static void btf_verifier_log_hdr(struct btf_verifier_env *env, + u32 btf_data_size) +{ + struct bpf_verifier_log *log = &env->log; + const struct btf *btf = env->btf; + const struct btf_header *hdr; + + if (!bpf_verifier_log_needed(log)) + return; + + hdr = &btf->hdr; + __btf_verifier_log(log, "magic: 0x%x\n", hdr->magic); + __btf_verifier_log(log, "version: %u\n", hdr->version); + __btf_verifier_log(log, "flags: 0x%x\n", hdr->flags); + __btf_verifier_log(log, "hdr_len: %u\n", hdr->hdr_len); + __btf_verifier_log(log, "type_off: %u\n", hdr->type_off); + __btf_verifier_log(log, "type_len: %u\n", hdr->type_len); + __btf_verifier_log(log, "str_off: %u\n", hdr->str_off); + __btf_verifier_log(log, "str_len: %u\n", hdr->str_len); + __btf_verifier_log(log, "btf_total_size: %u\n", btf_data_size); +} + +static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t) +{ + struct btf *btf = env->btf; + + /* < 2 because +1 for btf_void which is always in btf->types[0]. + * btf_void is not accounted in btf->nr_types because btf_void + * does not come from the BTF file. + */ + if (btf->types_size - btf->nr_types < 2) { + /* Expand 'types' array */ + + struct btf_type **new_types; + u32 expand_by, new_size; + + if (btf->types_size == BTF_MAX_TYPE) { + btf_verifier_log(env, "Exceeded max num of types"); + return -E2BIG; + } + + expand_by = max_t(u32, btf->types_size >> 2, 16); + new_size = min_t(u32, BTF_MAX_TYPE, + btf->types_size + expand_by); + + new_types = kvcalloc(new_size, sizeof(*new_types), + GFP_KERNEL | __GFP_NOWARN); + if (!new_types) + return -ENOMEM; + + if (btf->nr_types == 0) + new_types[0] = &btf_void; + else + memcpy(new_types, btf->types, + sizeof(*btf->types) * (btf->nr_types + 1)); + + kvfree(btf->types); + btf->types = new_types; + btf->types_size = new_size; + } + + btf->types[++(btf->nr_types)] = t; + + return 0; +} + +static int btf_alloc_id(struct btf *btf) +{ + int id; + + idr_preload(GFP_KERNEL); + spin_lock_bh(&btf_idr_lock); + id = idr_alloc_cyclic(&btf_idr, btf, 1, INT_MAX, GFP_ATOMIC); + if (id > 0) + btf->id = id; + spin_unlock_bh(&btf_idr_lock); + idr_preload_end(); + + if (WARN_ON_ONCE(!id)) + return -ENOSPC; + + return id > 0 ? 0 : id; +} + +static void btf_free_id(struct btf *btf) +{ + unsigned long flags; + + /* + * In map-in-map, calling map_delete_elem() on outer + * map will call bpf_map_put on the inner map. + * It will then eventually call btf_free_id() + * on the inner map. Some of the map_delete_elem() + * implementation may have irq disabled, so + * we need to use the _irqsave() version instead + * of the _bh() version. + */ + spin_lock_irqsave(&btf_idr_lock, flags); + idr_remove(&btf_idr, btf->id); + spin_unlock_irqrestore(&btf_idr_lock, flags); +} + +static void btf_free(struct btf *btf) +{ + kvfree(btf->types); + kvfree(btf->resolved_sizes); + kvfree(btf->resolved_ids); + kvfree(btf->data); + kfree(btf); +} + +static void btf_free_rcu(struct rcu_head *rcu) +{ + struct btf *btf = container_of(rcu, struct btf, rcu); + + btf_free(btf); +} + +void btf_put(struct btf *btf) +{ + if (btf && refcount_dec_and_test(&btf->refcnt)) { + btf_free_id(btf); + call_rcu(&btf->rcu, btf_free_rcu); + } +} + +static int env_resolve_init(struct btf_verifier_env *env) +{ + struct btf *btf = env->btf; + u32 nr_types = btf->nr_types; + u32 *resolved_sizes = NULL; + u32 *resolved_ids = NULL; + u8 *visit_states = NULL; + + /* +1 for btf_void */ + resolved_sizes = kvcalloc(nr_types + 1, sizeof(*resolved_sizes), + GFP_KERNEL | __GFP_NOWARN); + if (!resolved_sizes) + goto nomem; + + resolved_ids = kvcalloc(nr_types + 1, sizeof(*resolved_ids), + GFP_KERNEL | __GFP_NOWARN); + if (!resolved_ids) + goto nomem; + + visit_states = kvcalloc(nr_types + 1, sizeof(*visit_states), + GFP_KERNEL | __GFP_NOWARN); + if (!visit_states) + goto nomem; + + btf->resolved_sizes = resolved_sizes; + btf->resolved_ids = resolved_ids; + env->visit_states = visit_states; + + return 0; + +nomem: + kvfree(resolved_sizes); + kvfree(resolved_ids); + kvfree(visit_states); + return -ENOMEM; +} + +static void btf_verifier_env_free(struct btf_verifier_env *env) +{ + kvfree(env->visit_states); + kfree(env); +} + +static bool env_type_is_resolve_sink(const struct btf_verifier_env *env, + const struct btf_type *next_type) +{ + switch (env->resolve_mode) { + case RESOLVE_TBD: + /* int, enum or void is a sink */ + return !btf_type_needs_resolve(next_type); + case RESOLVE_PTR: + /* int, enum, void, struct or array is a sink for ptr */ + return !btf_type_is_modifier(next_type) && + !btf_type_is_ptr(next_type); + case RESOLVE_STRUCT_OR_ARRAY: + /* int, enum, void or ptr is a sink for struct and array */ + return !btf_type_is_modifier(next_type) && + !btf_type_is_array(next_type) && + !btf_type_is_struct(next_type); + default: + BUG(); + } +} + +static bool env_type_is_resolved(const struct btf_verifier_env *env, + u32 type_id) +{ + return env->visit_states[type_id] == RESOLVED; +} + +static int env_stack_push(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id) +{ + struct resolve_vertex *v; + + if (env->top_stack == MAX_RESOLVE_DEPTH) + return -E2BIG; + + if (env->visit_states[type_id] != NOT_VISITED) + return -EEXIST; + + env->visit_states[type_id] = VISITED; + + v = &env->stack[env->top_stack++]; + v->t = t; + v->type_id = type_id; + v->next_member = 0; + + if (env->resolve_mode == RESOLVE_TBD) { + if (btf_type_is_ptr(t)) + env->resolve_mode = RESOLVE_PTR; + else if (btf_type_is_struct(t) || btf_type_is_array(t)) + env->resolve_mode = RESOLVE_STRUCT_OR_ARRAY; + } + + return 0; +} + +static void env_stack_set_next_member(struct btf_verifier_env *env, + u16 next_member) +{ + env->stack[env->top_stack - 1].next_member = next_member; +} + +static void env_stack_pop_resolved(struct btf_verifier_env *env, + u32 resolved_type_id, + u32 resolved_size) +{ + u32 type_id = env->stack[--(env->top_stack)].type_id; + struct btf *btf = env->btf; + + btf->resolved_sizes[type_id] = resolved_size; + btf->resolved_ids[type_id] = resolved_type_id; + env->visit_states[type_id] = RESOLVED; +} + +static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env) +{ + return env->top_stack ? &env->stack[env->top_stack - 1] : NULL; +} + +/* The input param "type_id" must point to a needs_resolve type */ +static const struct btf_type *btf_type_id_resolve(const struct btf *btf, + u32 *type_id) +{ + *type_id = btf->resolved_ids[*type_id]; + return btf_type_by_id(btf, *type_id); +} + +const struct btf_type *btf_type_id_size(const struct btf *btf, + u32 *type_id, u32 *ret_size) +{ + const struct btf_type *size_type; + u32 size_type_id = *type_id; + u32 size = 0; + + size_type = btf_type_by_id(btf, size_type_id); + if (btf_type_is_void_or_null(size_type)) + return NULL; + + if (btf_type_has_size(size_type)) { + size = size_type->size; + } else if (btf_type_is_array(size_type)) { + size = btf->resolved_sizes[size_type_id]; + } else if (btf_type_is_ptr(size_type)) { + size = sizeof(void *); + } else { + if (WARN_ON_ONCE(!btf_type_is_modifier(size_type))) + return NULL; + + size = btf->resolved_sizes[size_type_id]; + size_type_id = btf->resolved_ids[size_type_id]; + size_type = btf_type_by_id(btf, size_type_id); + if (btf_type_is_void(size_type)) + return NULL; + } + + *type_id = size_type_id; + if (ret_size) + *ret_size = size; + + return size_type; +} + +static int btf_df_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + btf_verifier_log_basic(env, struct_type, + "Unsupported check_member"); + return -EINVAL; +} + +static int btf_df_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + btf_verifier_log_basic(env, v->t, "Unsupported resolve"); + return -EINVAL; +} + +static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offsets, + struct seq_file *m) +{ + seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info)); +} + +static int btf_int_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 int_data = btf_type_int(member_type); + u32 struct_bits_off = member->offset; + u32 struct_size = struct_type->size; + u32 nr_copy_bits; + u32 bytes_offset; + + if (U32_MAX - struct_bits_off < BTF_INT_OFFSET(int_data)) { + btf_verifier_log_member(env, struct_type, member, + "bits_offset exceeds U32_MAX"); + return -EINVAL; + } + + struct_bits_off += BTF_INT_OFFSET(int_data); + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + nr_copy_bits = BTF_INT_BITS(int_data) + + BITS_PER_BYTE_MASKED(struct_bits_off); + + if (nr_copy_bits > BITS_PER_U64) { + btf_verifier_log_member(env, struct_type, member, + "nr_copy_bits exceeds 64"); + return -EINVAL; + } + + if (struct_size < bytes_offset || + struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_int_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + u32 int_data, nr_bits, meta_needed = sizeof(int_data); + u16 encoding; + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + int_data = btf_type_int(t); + if (int_data & ~BTF_INT_MASK) { + btf_verifier_log_basic(env, t, "Invalid int_data:%x", + int_data); + return -EINVAL; + } + + nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data); + + if (nr_bits > BITS_PER_U64) { + btf_verifier_log_type(env, t, "nr_bits exceeds %zu", + BITS_PER_U64); + return -EINVAL; + } + + if (BITS_ROUNDUP_BYTES(nr_bits) > t->size) { + btf_verifier_log_type(env, t, "nr_bits exceeds type_size"); + return -EINVAL; + } + + /* + * Only one of the encoding bits is allowed and it + * should be sufficient for the pretty print purpose (i.e. decoding). + * Multiple bits can be allowed later if it is found + * to be insufficient. + */ + encoding = BTF_INT_ENCODING(int_data); + if (encoding && + encoding != BTF_INT_SIGNED && + encoding != BTF_INT_CHAR && + encoding != BTF_INT_BOOL) { + btf_verifier_log_type(env, t, "Unsupported encoding"); + return -ENOTSUPP; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static void btf_int_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + int int_data = btf_type_int(t); + + btf_verifier_log(env, + "size=%u bits_offset=%u nr_bits=%u encoding=%s", + t->size, BTF_INT_OFFSET(int_data), + BTF_INT_BITS(int_data), + btf_int_encoding_str(BTF_INT_ENCODING(int_data))); +} + +static void btf_int_bits_seq_show(const struct btf *btf, + const struct btf_type *t, + void *data, u8 bits_offset, + struct seq_file *m) +{ + u16 left_shift_bits, right_shift_bits; + u32 int_data = btf_type_int(t); + u8 nr_bits = BTF_INT_BITS(int_data); + u8 total_bits_offset; + u8 nr_copy_bytes; + u8 nr_copy_bits; + u64 print_num; + + /* + * bits_offset is at most 7. + * BTF_INT_OFFSET() cannot exceed 64 bits. + */ + total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); + data += BITS_ROUNDDOWN_BYTES(total_bits_offset); + bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); + nr_copy_bits = nr_bits + bits_offset; + nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); + + print_num = 0; + memcpy(&print_num, data, nr_copy_bytes); + +#ifdef __BIG_ENDIAN_BITFIELD + left_shift_bits = bits_offset; +#else + left_shift_bits = BITS_PER_U64 - nr_copy_bits; +#endif + right_shift_bits = BITS_PER_U64 - nr_bits; + + print_num <<= left_shift_bits; + print_num >>= right_shift_bits; + + seq_printf(m, "0x%llx", print_num); +} + +static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + u32 int_data = btf_type_int(t); + u8 encoding = BTF_INT_ENCODING(int_data); + bool sign = encoding & BTF_INT_SIGNED; + u8 nr_bits = BTF_INT_BITS(int_data); + + if (bits_offset || BTF_INT_OFFSET(int_data) || + BITS_PER_BYTE_MASKED(nr_bits)) { + btf_int_bits_seq_show(btf, t, data, bits_offset, m); + return; + } + + switch (nr_bits) { + case 64: + if (sign) + seq_printf(m, "%lld", *(s64 *)data); + else + seq_printf(m, "%llu", *(u64 *)data); + break; + case 32: + if (sign) + seq_printf(m, "%d", *(s32 *)data); + else + seq_printf(m, "%u", *(u32 *)data); + break; + case 16: + if (sign) + seq_printf(m, "%d", *(s16 *)data); + else + seq_printf(m, "%u", *(u16 *)data); + break; + case 8: + if (sign) + seq_printf(m, "%d", *(s8 *)data); + else + seq_printf(m, "%u", *(u8 *)data); + break; + default: + btf_int_bits_seq_show(btf, t, data, bits_offset, m); + } +} + +static const struct btf_kind_operations int_ops = { + .check_meta = btf_int_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_int_check_member, + .log_details = btf_int_log, + .seq_show = btf_int_seq_show, +}; + +static int btf_modifier_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + const struct btf_type *resolved_type; + u32 resolved_type_id = member->type; + struct btf_member resolved_member; + struct btf *btf = env->btf; + + resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL); + if (!resolved_type) { + btf_verifier_log_member(env, struct_type, member, + "Invalid member"); + return -EINVAL; + } + + resolved_member = *member; + resolved_member.type = resolved_type_id; + + return btf_type_ops(resolved_type)->check_member(env, struct_type, + &resolved_member, + resolved_type); +} + +static int btf_ptr_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_size, struct_bits_off, bytes_offset; + + struct_size = struct_type->size; + struct_bits_off = member->offset; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + if (struct_size - bytes_offset < sizeof(void *)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static int btf_ref_type_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (!BTF_TYPE_ID_VALID(t->type)) { + btf_verifier_log_type(env, t, "Invalid type_id"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return 0; +} + +static int btf_modifier_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *t = v->t; + const struct btf_type *next_type; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + u32 next_type_size = 0; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + /* "typedef void new_void", "const void"...etc */ + if (btf_type_is_void(next_type)) + goto resolved; + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + /* Figure out the resolved next_type_id with size. + * They will be stored in the current modifier's + * resolved_ids and resolved_sizes such that it can + * save us a few type-following when we use it later (e.g. in + * pretty print). + */ + if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && + !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + +resolved: + env_stack_pop_resolved(env, next_type_id, next_type_size); + + return 0; +} + +static int btf_ptr_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *next_type; + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + u32 next_type_size = 0; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + /* "void *" */ + if (btf_type_is_void(next_type)) + goto resolved; + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + /* If the modifier was RESOLVED during RESOLVE_STRUCT_OR_ARRAY, + * the modifier may have stopped resolving when it was resolved + * to a ptr (last-resolved-ptr). + * + * We now need to continue from the last-resolved-ptr to + * ensure the last-resolved-ptr will not referring back to + * the currenct ptr (t). + */ + if (btf_type_is_modifier(next_type)) { + const struct btf_type *resolved_type; + u32 resolved_type_id; + + resolved_type_id = next_type_id; + resolved_type = btf_type_id_resolve(btf, &resolved_type_id); + + if (btf_type_is_ptr(resolved_type) && + !env_type_is_resolve_sink(env, resolved_type) && + !env_type_is_resolved(env, resolved_type_id)) + return env_stack_push(env, resolved_type, + resolved_type_id); + } + + if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && + !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + +resolved: + env_stack_pop_resolved(env, next_type_id, 0); + + return 0; +} + +static void btf_modifier_seq_show(const struct btf *btf, + const struct btf_type *t, + u32 type_id, void *data, + u8 bits_offset, struct seq_file *m) +{ + t = btf_type_id_resolve(btf, &type_id); + + btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m); +} + +static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + /* It is a hashed value */ + seq_printf(m, "%p", *(void **)data); +} + +static void btf_ref_type_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "type_id=%u", t->type); +} + +static struct btf_kind_operations modifier_ops = { + .check_meta = btf_ref_type_check_meta, + .resolve = btf_modifier_resolve, + .check_member = btf_modifier_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_modifier_seq_show, +}; + +static struct btf_kind_operations ptr_ops = { + .check_meta = btf_ref_type_check_meta, + .resolve = btf_ptr_resolve, + .check_member = btf_ptr_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_ptr_seq_show, +}; + +static s32 btf_fwd_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (t->type) { + btf_verifier_log_type(env, t, "type != 0"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return 0; +} + +static struct btf_kind_operations fwd_ops = { + .check_meta = btf_fwd_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_df_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_df_seq_show, +}; + +static int btf_array_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off = member->offset; + u32 struct_size, bytes_offset; + u32 array_type_id, array_size; + struct btf *btf = env->btf; + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + array_type_id = member->type; + btf_type_id_size(btf, &array_type_id, &array_size); + struct_size = struct_type->size; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + if (struct_size - bytes_offset < array_size) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_array_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_array *array = btf_type_array(t); + u32 meta_needed = sizeof(*array); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (t->size) { + btf_verifier_log_type(env, t, "size != 0"); + return -EINVAL; + } + + /* Array elem type and index type cannot be in type void, + * so !array->type and !array->index_type are not allowed. + */ + if (!array->type || !BTF_TYPE_ID_VALID(array->type)) { + btf_verifier_log_type(env, t, "Invalid elem"); + return -EINVAL; + } + + if (!array->index_type || !BTF_TYPE_ID_VALID(array->index_type)) { + btf_verifier_log_type(env, t, "Invalid index"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static int btf_array_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_array *array = btf_type_array(v->t); + const struct btf_type *elem_type, *index_type; + u32 elem_type_id, index_type_id; + struct btf *btf = env->btf; + u32 elem_size; + + /* Check array->index_type */ + index_type_id = array->index_type; + index_type = btf_type_by_id(btf, index_type_id); + if (btf_type_is_void_or_null(index_type)) { + btf_verifier_log_type(env, v->t, "Invalid index"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, index_type) && + !env_type_is_resolved(env, index_type_id)) + return env_stack_push(env, index_type, index_type_id); + + index_type = btf_type_id_size(btf, &index_type_id, NULL); + if (!index_type || !btf_type_is_int(index_type) || + !btf_type_int_is_regular(index_type)) { + btf_verifier_log_type(env, v->t, "Invalid index"); + return -EINVAL; + } + + /* Check array->type */ + elem_type_id = array->type; + elem_type = btf_type_by_id(btf, elem_type_id); + if (btf_type_is_void_or_null(elem_type)) { + btf_verifier_log_type(env, v->t, + "Invalid elem"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, elem_type) && + !env_type_is_resolved(env, elem_type_id)) + return env_stack_push(env, elem_type, elem_type_id); + + elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + if (!elem_type) { + btf_verifier_log_type(env, v->t, "Invalid elem"); + return -EINVAL; + } + + if (btf_type_is_int(elem_type) && !btf_type_int_is_regular(elem_type)) { + btf_verifier_log_type(env, v->t, "Invalid array of int"); + return -EINVAL; + } + + if (array->nelems && elem_size > U32_MAX / array->nelems) { + btf_verifier_log_type(env, v->t, + "Array size overflows U32_MAX"); + return -EINVAL; + } + + env_stack_pop_resolved(env, elem_type_id, elem_size * array->nelems); + + return 0; +} + +static void btf_array_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + const struct btf_array *array = btf_type_array(t); + + btf_verifier_log(env, "type_id=%u index_type_id=%u nr_elems=%u", + array->type, array->index_type, array->nelems); +} + +static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + const struct btf_array *array = btf_type_array(t); + const struct btf_kind_operations *elem_ops; + const struct btf_type *elem_type; + u32 i, elem_size, elem_type_id; + + elem_type_id = array->type; + elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + elem_ops = btf_type_ops(elem_type); + seq_puts(m, "["); + for (i = 0; i < array->nelems; i++) { + if (i) + seq_puts(m, ","); + + elem_ops->seq_show(btf, elem_type, elem_type_id, data, + bits_offset, m); + data += elem_size; + } + seq_puts(m, "]"); +} + +static struct btf_kind_operations array_ops = { + .check_meta = btf_array_check_meta, + .resolve = btf_array_resolve, + .check_member = btf_array_check_member, + .log_details = btf_array_log, + .seq_show = btf_array_seq_show, +}; + +static int btf_struct_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off = member->offset; + u32 struct_size, bytes_offset; + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + struct_size = struct_type->size; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + if (struct_size - bytes_offset < member_type->size) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_struct_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION; + const struct btf_member *member; + u32 meta_needed, last_offset; + struct btf *btf = env->btf; + u32 struct_size = t->size; + u16 i; + + meta_needed = btf_type_vlen(t) * sizeof(*member); + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + last_offset = 0; + for_each_member(i, t, member) { + if (!btf_name_offset_valid(btf, member->name_off)) { + btf_verifier_log_member(env, t, member, + "Invalid member name_offset:%u", + member->name_off); + return -EINVAL; + } + + /* A member cannot be in type void */ + if (!member->type || !BTF_TYPE_ID_VALID(member->type)) { + btf_verifier_log_member(env, t, member, + "Invalid type_id"); + return -EINVAL; + } + + if (is_union && member->offset) { + btf_verifier_log_member(env, t, member, + "Invalid member bits_offset"); + return -EINVAL; + } + + /* + * ">" instead of ">=" because the last member could be + * "char a[0];" + */ + if (last_offset > member->offset) { + btf_verifier_log_member(env, t, member, + "Invalid member bits_offset"); + return -EINVAL; + } + + if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) { + btf_verifier_log_member(env, t, member, + "Memmber bits_offset exceeds its struct size"); + return -EINVAL; + } + + btf_verifier_log_member(env, t, member, NULL); + last_offset = member->offset; + } + + return meta_needed; +} + +static int btf_struct_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_member *member; + int err; + u16 i; + + /* Before continue resolving the next_member, + * ensure the last member is indeed resolved to a + * type with size info. + */ + if (v->next_member) { + const struct btf_type *last_member_type; + const struct btf_member *last_member; + u16 last_member_type_id; + + last_member = btf_type_member(v->t) + v->next_member - 1; + last_member_type_id = last_member->type; + if (WARN_ON_ONCE(!env_type_is_resolved(env, + last_member_type_id))) + return -EINVAL; + + last_member_type = btf_type_by_id(env->btf, + last_member_type_id); + err = btf_type_ops(last_member_type)->check_member(env, v->t, + last_member, + last_member_type); + if (err) + return err; + } + + for_each_member_from(i, v->next_member, v->t, member) { + u32 member_type_id = member->type; + const struct btf_type *member_type = btf_type_by_id(env->btf, + member_type_id); + + if (btf_type_is_void_or_null(member_type)) { + btf_verifier_log_member(env, v->t, member, + "Invalid member"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, member_type) && + !env_type_is_resolved(env, member_type_id)) { + env_stack_set_next_member(env, i + 1); + return env_stack_push(env, member_type, member_type_id); + } + + err = btf_type_ops(member_type)->check_member(env, v->t, + member, + member_type); + if (err) + return err; + } + + env_stack_pop_resolved(env, 0, 0); + + return 0; +} + +static void btf_struct_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); +} + +static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ","; + const struct btf_member *member; + u32 i; + + seq_puts(m, "{"); + for_each_member(i, t, member) { + const struct btf_type *member_type = btf_type_by_id(btf, + member->type); + u32 member_offset = member->offset; + u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); + u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset); + const struct btf_kind_operations *ops; + + if (i) + seq_puts(m, seq); + + ops = btf_type_ops(member_type); + ops->seq_show(btf, member_type, member->type, + data + bytes_offset, bits8_offset, m); + } + seq_puts(m, "}"); +} + +static struct btf_kind_operations struct_ops = { + .check_meta = btf_struct_check_meta, + .resolve = btf_struct_resolve, + .check_member = btf_struct_check_member, + .log_details = btf_struct_log, + .seq_show = btf_struct_seq_show, +}; + +static int btf_enum_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off = member->offset; + u32 struct_size, bytes_offset; + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + struct_size = struct_type->size; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + if (struct_size - bytes_offset < sizeof(int)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_enum_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_enum *enums = btf_type_enum(t); + struct btf *btf = env->btf; + u16 i, nr_enums; + u32 meta_needed; + + nr_enums = btf_type_vlen(t); + meta_needed = nr_enums * sizeof(*enums); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (t->size != sizeof(int)) { + btf_verifier_log_type(env, t, "Expected size:%zu", + sizeof(int)); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + for (i = 0; i < nr_enums; i++) { + if (!btf_name_offset_valid(btf, enums[i].name_off)) { + btf_verifier_log(env, "\tInvalid name_offset:%u", + enums[i].name_off); + return -EINVAL; + } + + btf_verifier_log(env, "\t%s val=%d\n", + btf_name_by_offset(btf, enums[i].name_off), + enums[i].val); + } + + return meta_needed; +} + +static void btf_enum_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); +} + +static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + const struct btf_enum *enums = btf_type_enum(t); + u32 i, nr_enums = btf_type_vlen(t); + int v = *(int *)data; + + for (i = 0; i < nr_enums; i++) { + if (v == enums[i].val) { + seq_printf(m, "%s", + btf_name_by_offset(btf, enums[i].name_off)); + return; + } + } + + seq_printf(m, "%d", v); +} + +static struct btf_kind_operations enum_ops = { + .check_meta = btf_enum_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_enum_check_member, + .log_details = btf_enum_log, + .seq_show = btf_enum_seq_show, +}; + +static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { + [BTF_KIND_INT] = &int_ops, + [BTF_KIND_PTR] = &ptr_ops, + [BTF_KIND_ARRAY] = &array_ops, + [BTF_KIND_STRUCT] = &struct_ops, + [BTF_KIND_UNION] = &struct_ops, + [BTF_KIND_ENUM] = &enum_ops, + [BTF_KIND_FWD] = &fwd_ops, + [BTF_KIND_TYPEDEF] = &modifier_ops, + [BTF_KIND_VOLATILE] = &modifier_ops, + [BTF_KIND_CONST] = &modifier_ops, + [BTF_KIND_RESTRICT] = &modifier_ops, +}; + +static s32 btf_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + u32 saved_meta_left = meta_left; + s32 var_meta_size; + + if (meta_left < sizeof(*t)) { + btf_verifier_log(env, "[%u] meta_left:%u meta_needed:%zu", + env->log_type_id, meta_left, sizeof(*t)); + return -EINVAL; + } + meta_left -= sizeof(*t); + + if (t->info & ~BTF_INFO_MASK) { + btf_verifier_log(env, "[%u] Invalid btf_info:%x", + env->log_type_id, t->info); + return -EINVAL; + } + + if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX || + BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) { + btf_verifier_log(env, "[%u] Invalid kind:%u", + env->log_type_id, BTF_INFO_KIND(t->info)); + return -EINVAL; + } + + if (!btf_name_offset_valid(env->btf, t->name_off)) { + btf_verifier_log(env, "[%u] Invalid name_offset:%u", + env->log_type_id, t->name_off); + return -EINVAL; + } + + var_meta_size = btf_type_ops(t)->check_meta(env, t, meta_left); + if (var_meta_size < 0) + return var_meta_size; + + meta_left -= var_meta_size; + + return saved_meta_left - meta_left; +} + +static int btf_check_all_metas(struct btf_verifier_env *env) +{ + struct btf *btf = env->btf; + struct btf_header *hdr; + void *cur, *end; + + hdr = &btf->hdr; + cur = btf->nohdr_data + hdr->type_off; + end = btf->nohdr_data + hdr->type_len; + + env->log_type_id = 1; + while (cur < end) { + struct btf_type *t = cur; + s32 meta_size; + + meta_size = btf_check_meta(env, t, end - cur); + if (meta_size < 0) + return meta_size; + + btf_add_type(env, t); + cur += meta_size; + env->log_type_id++; + } + + return 0; +} + +static int btf_resolve(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id) +{ + const struct resolve_vertex *v; + int err = 0; + + env->resolve_mode = RESOLVE_TBD; + env_stack_push(env, t, type_id); + while (!err && (v = env_stack_peak(env))) { + env->log_type_id = v->type_id; + err = btf_type_ops(v->t)->resolve(env, v); + } + + env->log_type_id = type_id; + if (err == -E2BIG) + btf_verifier_log_type(env, t, + "Exceeded max resolving depth:%u", + MAX_RESOLVE_DEPTH); + else if (err == -EEXIST) + btf_verifier_log_type(env, t, "Loop detected"); + + return err; +} + +static bool btf_resolve_valid(struct btf_verifier_env *env, + const struct btf_type *t, + u32 type_id) +{ + struct btf *btf = env->btf; + + if (!env_type_is_resolved(env, type_id)) + return false; + + if (btf_type_is_struct(t)) + return !btf->resolved_ids[type_id] && + !btf->resolved_sizes[type_id]; + + if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) { + t = btf_type_id_resolve(btf, &type_id); + return t && !btf_type_is_modifier(t); + } + + if (btf_type_is_array(t)) { + const struct btf_array *array = btf_type_array(t); + const struct btf_type *elem_type; + u32 elem_type_id = array->type; + u32 elem_size; + + elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + return elem_type && !btf_type_is_modifier(elem_type) && + (array->nelems * elem_size == + btf->resolved_sizes[type_id]); + } + + return false; +} + +static int btf_check_all_types(struct btf_verifier_env *env) +{ + struct btf *btf = env->btf; + u32 type_id; + int err; + + err = env_resolve_init(env); + if (err) + return err; + + env->phase++; + for (type_id = 1; type_id <= btf->nr_types; type_id++) { + const struct btf_type *t = btf_type_by_id(btf, type_id); + + env->log_type_id = type_id; + if (btf_type_needs_resolve(t) && + !env_type_is_resolved(env, type_id)) { + err = btf_resolve(env, t, type_id); + if (err) + return err; + } + + if (btf_type_needs_resolve(t) && + !btf_resolve_valid(env, t, type_id)) { + btf_verifier_log_type(env, t, "Invalid resolve state"); + return -EINVAL; + } + } + + return 0; +} + +static int btf_parse_type_sec(struct btf_verifier_env *env) +{ + const struct btf_header *hdr = &env->btf->hdr; + int err; + + /* Type section must align to 4 bytes */ + if (hdr->type_off & (sizeof(u32) - 1)) { + btf_verifier_log(env, "Unaligned type_off"); + return -EINVAL; + } + + if (!hdr->type_len) { + btf_verifier_log(env, "No type found"); + return -EINVAL; + } + + err = btf_check_all_metas(env); + if (err) + return err; + + return btf_check_all_types(env); +} + +static int btf_parse_str_sec(struct btf_verifier_env *env) +{ + const struct btf_header *hdr; + struct btf *btf = env->btf; + const char *start, *end; + + hdr = &btf->hdr; + start = btf->nohdr_data + hdr->str_off; + end = start + hdr->str_len; + + if (end != btf->data + btf->data_size) { + btf_verifier_log(env, "String section is not at the end"); + return -EINVAL; + } + + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || + start[0] || end[-1]) { + btf_verifier_log(env, "Invalid string section"); + return -EINVAL; + } + + btf->strings = start; + + return 0; +} + +static const size_t btf_sec_info_offset[] = { + offsetof(struct btf_header, type_off), + offsetof(struct btf_header, str_off), +}; + +static int btf_sec_info_cmp(const void *a, const void *b) +{ + const struct btf_sec_info *x = a; + const struct btf_sec_info *y = b; + + return (int)(x->off - y->off) ? : (int)(x->len - y->len); +} + +static int btf_check_sec_info(struct btf_verifier_env *env, + u32 btf_data_size) +{ + struct btf_sec_info secs[ARRAY_SIZE(btf_sec_info_offset)]; + u32 total, expected_total, i; + const struct btf_header *hdr; + const struct btf *btf; + + btf = env->btf; + hdr = &btf->hdr; + + /* Populate the secs from hdr */ + for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++) + secs[i] = *(struct btf_sec_info *)((void *)hdr + + btf_sec_info_offset[i]); + + sort(secs, ARRAY_SIZE(btf_sec_info_offset), + sizeof(struct btf_sec_info), btf_sec_info_cmp, NULL); + + /* Check for gaps and overlap among sections */ + total = 0; + expected_total = btf_data_size - hdr->hdr_len; + for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++) { + if (expected_total < secs[i].off) { + btf_verifier_log(env, "Invalid section offset"); + return -EINVAL; + } + if (total < secs[i].off) { + /* gap */ + btf_verifier_log(env, "Unsupported section found"); + return -EINVAL; + } + if (total > secs[i].off) { + btf_verifier_log(env, "Section overlap found"); + return -EINVAL; + } + if (expected_total - total < secs[i].len) { + btf_verifier_log(env, + "Total section length too long"); + return -EINVAL; + } + total += secs[i].len; + } + + /* There is data other than hdr and known sections */ + if (expected_total != total) { + btf_verifier_log(env, "Unsupported section found"); + return -EINVAL; + } + + return 0; +} + +static int btf_parse_hdr(struct btf_verifier_env *env, void __user *btf_data, + u32 btf_data_size) +{ + const struct btf_header *hdr; + u32 hdr_len, hdr_copy; + /* + * Minimal part of the "struct btf_header" that + * contains the hdr_len. + */ + struct btf_min_header { + u16 magic; + u8 version; + u8 flags; + u32 hdr_len; + } __user *min_hdr; + struct btf *btf; + int err; + + btf = env->btf; + min_hdr = btf_data; + + if (btf_data_size < sizeof(*min_hdr)) { + btf_verifier_log(env, "hdr_len not found"); + return -EINVAL; + } + + if (get_user(hdr_len, &min_hdr->hdr_len)) + return -EFAULT; + + if (btf_data_size < hdr_len) { + btf_verifier_log(env, "btf_header not found"); + return -EINVAL; + } + + err = bpf_check_uarg_tail_zero(btf_data, sizeof(btf->hdr), hdr_len); + if (err) { + if (err == -E2BIG) + btf_verifier_log(env, "Unsupported btf_header"); + return err; + } + + hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr)); + if (copy_from_user(&btf->hdr, btf_data, hdr_copy)) + return -EFAULT; + + hdr = &btf->hdr; + + btf_verifier_log_hdr(env, btf_data_size); + + if (hdr->magic != BTF_MAGIC) { + btf_verifier_log(env, "Invalid magic"); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + btf_verifier_log(env, "Unsupported version"); + return -ENOTSUPP; + } + + if (hdr->flags) { + btf_verifier_log(env, "Unsupported flags"); + return -ENOTSUPP; + } + + if (btf_data_size == hdr->hdr_len) { + btf_verifier_log(env, "No data"); + return -EINVAL; + } + + err = btf_check_sec_info(env, btf_data_size); + if (err) + return err; + + return 0; +} + +static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, + u32 log_level, char __user *log_ubuf, u32 log_size) +{ + struct btf_verifier_env *env = NULL; + struct bpf_verifier_log *log; + struct btf *btf = NULL; + u8 *data; + int err; + + if (btf_data_size > BTF_MAX_SIZE) + return ERR_PTR(-E2BIG); + + env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); + if (!env) + return ERR_PTR(-ENOMEM); + + log = &env->log; + if (log_level || log_ubuf || log_size) { + /* user requested verbose verifier output + * and supplied buffer to store the verification trace + */ + log->level = log_level; + log->ubuf = log_ubuf; + log->len_total = log_size; + + /* log attributes have to be sane */ + if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || + !log->level || !log->ubuf) { + err = -EINVAL; + goto errout; + } + } + + btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); + if (!btf) { + err = -ENOMEM; + goto errout; + } + env->btf = btf; + + err = btf_parse_hdr(env, btf_data, btf_data_size); + if (err) + goto errout; + + data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); + if (!data) { + err = -ENOMEM; + goto errout; + } + + btf->data = data; + btf->data_size = btf_data_size; + btf->nohdr_data = btf->data + btf->hdr.hdr_len; + + if (copy_from_user(data, btf_data, btf_data_size)) { + err = -EFAULT; + goto errout; + } + + err = btf_parse_str_sec(env); + if (err) + goto errout; + + err = btf_parse_type_sec(env); + if (err) + goto errout; + + if (log->level && bpf_verifier_log_full(log)) { + err = -ENOSPC; + goto errout; + } + + btf_verifier_env_free(env); + refcount_set(&btf->refcnt, 1); + return btf; + +errout: + btf_verifier_env_free(env); + if (btf) + btf_free(btf); + return ERR_PTR(err); +} + +void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, + struct seq_file *m) +{ + const struct btf_type *t = btf_type_by_id(btf, type_id); + + btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m); +} + +static int btf_release(struct inode *inode, struct file *filp) +{ + btf_put(filp->private_data); + return 0; +} + +const struct file_operations btf_fops = { + .release = btf_release, +}; + +static int __btf_new_fd(struct btf *btf) +{ + return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC); +} + +int btf_new_fd(const union bpf_attr *attr) +{ + struct btf *btf; + int ret; + + btf = btf_parse(u64_to_user_ptr(attr->btf), + attr->btf_size, attr->btf_log_level, + u64_to_user_ptr(attr->btf_log_buf), + attr->btf_log_size); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + ret = btf_alloc_id(btf); + if (ret) { + btf_free(btf); + return ret; + } + + /* + * The BTF ID is published to the userspace. + * All BTF free must go through call_rcu() from + * now on (i.e. free by calling btf_put()). + */ + + ret = __btf_new_fd(btf); + if (ret < 0) + btf_put(btf); + + return ret; +} + +struct btf *btf_get_by_fd(int fd) +{ + struct btf *btf; + struct fd f; + + f = fdget(fd); + + if (!f.file) + return ERR_PTR(-EBADF); + + if (f.file->f_op != &btf_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + btf = f.file->private_data; + refcount_inc(&btf->refcnt); + fdput(f); + + return btf; +} + +int btf_get_info_by_fd(const struct btf *btf, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_btf_info __user *uinfo; + struct bpf_btf_info info = {}; + u32 info_copy, btf_copy; + void __user *ubtf; + u32 uinfo_len; + + uinfo = u64_to_user_ptr(attr->info.info); + uinfo_len = attr->info.info_len; + + info_copy = min_t(u32, uinfo_len, sizeof(info)); + if (copy_from_user(&info, uinfo, info_copy)) + return -EFAULT; + + info.id = btf->id; + ubtf = u64_to_user_ptr(info.btf); + btf_copy = min_t(u32, btf->data_size, info.btf_size); + if (copy_to_user(ubtf, btf->data, btf_copy)) + return -EFAULT; + info.btf_size = btf->data_size; + + if (copy_to_user(uinfo, &info, info_copy) || + put_user(info_copy, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} + +int btf_get_fd_by_id(u32 id) +{ + struct btf *btf; + int fd; + + rcu_read_lock(); + btf = idr_find(&btf_idr, id); + if (!btf || !refcount_inc_not_zero(&btf->refcnt)) + btf = ERR_PTR(-ENOENT); + rcu_read_unlock(); + + if (IS_ERR(btf)) + return PTR_ERR(btf); + + fd = __btf_new_fd(btf); + if (fd < 0) + btf_put(btf); + + return fd; +} + +u32 btf_id(const struct btf *btf) +{ + return btf->id; +} diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 43171a0bb02b..3d83ee7df381 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -428,6 +428,60 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, return ret; } +int cgroup_bpf_prog_attach(const union bpf_attr *attr, + enum bpf_prog_type ptype, struct bpf_prog *prog) +{ + struct cgroup *cgrp; + int ret; + + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + attr->attach_flags); + cgroup_put(cgrp); + return ret; +} + +int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + struct bpf_prog *prog; + struct cgroup *cgrp; + int ret; + + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + prog = NULL; + + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); + if (prog) + bpf_prog_put(prog); + + cgroup_put(cgrp); + return ret; +} + +int cgroup_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct cgroup *cgrp; + int ret; + + cgrp = cgroup_get_from_fd(attr->query.target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + ret = cgroup_bpf_query(cgrp, attr, uattr); + + cgroup_put(cgrp); + return ret; +} + /** * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic @@ -500,6 +554,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user * @type: The type of program to be exectuted + * @t_ctx: Pointer to attach type specific context * * socket is expected to be of type INET or INET6. * @@ -508,12 +563,15 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type) + enum bpf_attach_type type, + void *t_ctx) { struct bpf_sock_addr_kern ctx = { .sk = sk, .uaddr = uaddr, + .t_ctx = t_ctx, }; + struct sockaddr_storage unspec; struct cgroup *cgrp; int ret; @@ -523,6 +581,11 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; + if (!ctx.uaddr) { + memset(&unspec, 0, sizeof(unspec)); + ctx.uaddr = (struct sockaddr *)&unspec; + } + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6ef6746a7871..1e5625d46414 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -31,6 +31,7 @@ #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> +#include <linux/perf_event.h> #include <asm/unaligned.h> @@ -349,6 +350,20 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, return prog_adj; } +void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) +{ + int i; + + for (i = 0; i < fp->aux->func_cnt; i++) + bpf_prog_kallsyms_del(fp->aux->func[i]); +} + +void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) +{ + bpf_prog_kallsyms_del_subprogs(fp); + bpf_prog_kallsyms_del(fp); +} + #ifdef CONFIG_BPF_JIT /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); @@ -683,23 +698,6 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; - case BPF_LD | BPF_ABS | BPF_W: - case BPF_LD | BPF_ABS | BPF_H: - case BPF_LD | BPF_ABS | BPF_B: - *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); - *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); - break; - - case BPF_LD | BPF_IND | BPF_W: - case BPF_LD | BPF_IND | BPF_H: - case BPF_LD | BPF_IND | BPF_B: - *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); - *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg); - *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); - break; - case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); @@ -940,14 +938,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ /* Immediate based. */ \ - INSN_3(LD, IMM, DW), \ - /* Misc (old cBPF carry-over). */ \ - INSN_3(LD, ABS, B), \ - INSN_3(LD, ABS, H), \ - INSN_3(LD, ABS, W), \ - INSN_3(LD, IND, B), \ - INSN_3(LD, IND, H), \ - INSN_3(LD, IND, W) + INSN_3(LD, IMM, DW) bool bpf_opcode_in_insntable(u8 code) { @@ -957,6 +948,13 @@ bool bpf_opcode_in_insntable(u8 code) [0 ... 255] = false, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL), + /* UAPI exposed, but rewritten opcodes. cBPF carry-over. */ + [BPF_LD | BPF_ABS | BPF_B] = true, + [BPF_LD | BPF_ABS | BPF_H] = true, + [BPF_LD | BPF_ABS | BPF_W] = true, + [BPF_LD | BPF_IND | BPF_B] = true, + [BPF_LD | BPF_IND | BPF_H] = true, + [BPF_LD | BPF_IND | BPF_W] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL @@ -987,8 +985,6 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL u32 tail_call_cnt = 0; - void *ptr; - int off; #define CONT ({ insn++; goto select_insn; }) #define CONT_JMP ({ insn++; goto select_insn; }) @@ -1315,67 +1311,6 @@ out: atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) (DST + insn->off)); CONT; - LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ - off = IMM; -load_word: - /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only - * appearing in the programs where ctx == skb - * (see may_access_skb() in the verifier). All programs - * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6, - * bpf_convert_filter() saves it in BPF_R6, internal BPF - * verifier will check that BPF_R6 == ctx. - * - * BPF_ABS and BPF_IND are wrappers of function calls, - * so they scratch BPF_R1-BPF_R5 registers, preserve - * BPF_R6-BPF_R9, and store return value into BPF_R0. - * - * Implicit input: - * ctx == skb == BPF_R6 == CTX - * - * Explicit input: - * SRC == any register - * IMM == 32-bit immediate - * - * Output: - * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness - */ - - ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be32(ptr); - CONT; - } - - return 0; - LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */ - off = IMM; -load_half: - ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be16(ptr); - CONT; - } - - return 0; - LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */ - off = IMM; -load_byte: - ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = *(u8 *)ptr; - CONT; - } - - return 0; - LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_word; - LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_half; - LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */ - off = IMM + SRC; - goto load_byte; default_label: /* If we ever reach this, we have a bug somewhere. Die hard here @@ -1513,6 +1448,17 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) return 0; } +static void bpf_prog_select_func(struct bpf_prog *fp) +{ +#ifndef CONFIG_BPF_JIT_ALWAYS_ON + u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); + + fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; +#else + fp->bpf_func = __bpf_prog_ret0_warn; +#endif +} + /** * bpf_prog_select_runtime - select exec runtime for BPF program * @fp: bpf_prog populated with internal BPF program @@ -1523,13 +1469,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { -#ifndef CONFIG_BPF_JIT_ALWAYS_ON - u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); + /* In case of BPF to BPF calls, verifier did all the prep + * work with regards to JITing, etc. + */ + if (fp->bpf_func) + goto finalize; - fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; -#else - fp->bpf_func = __bpf_prog_ret0_warn; -#endif + bpf_prog_select_func(fp); /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during @@ -1550,6 +1496,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) if (*err) return fp; } + +finalize: bpf_prog_lock_ro(fp); /* The tail call compatibility check can only be done at @@ -1695,6 +1643,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, int new_prog_cnt, carry_prog_cnt = 0; struct bpf_prog **existing_prog; struct bpf_prog_array *array; + bool found_exclude = false; int new_prog_idx = 0; /* Figure out how many existing progs we need to carry over to @@ -1703,14 +1652,20 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, if (old_array) { existing_prog = old_array->progs; for (; *existing_prog; existing_prog++) { - if (*existing_prog != exclude_prog && - *existing_prog != &dummy_bpf_prog.prog) + if (*existing_prog == exclude_prog) { + found_exclude = true; + continue; + } + if (*existing_prog != &dummy_bpf_prog.prog) carry_prog_cnt++; if (*existing_prog == include_prog) return -EEXIST; } } + if (exclude_prog && !found_exclude) + return -ENOENT; + /* How many progs (not NULL) will be in the new array? */ new_prog_cnt = carry_prog_cnt; if (include_prog) @@ -1772,6 +1727,10 @@ static void bpf_prog_free_deferred(struct work_struct *work) aux = container_of(work, struct bpf_prog_aux, work); if (bpf_prog_is_dev_bound(aux)) bpf_prog_offload_destroy(aux->prog); +#ifdef CONFIG_PERF_EVENTS + if (aux->prog->has_callchain_buf) + put_callchain_buffers(); +#endif for (i = 0; i < aux->func_cnt; i++) bpf_jit_free(aux->func[i]); if (aux->func_cnt) { @@ -1832,6 +1791,8 @@ const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_sock_map_update_proto __weak; +const struct bpf_func_proto bpf_sock_hash_update_proto __weak; +const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { @@ -1844,6 +1805,7 @@ bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, { return -ENOTSUPP; } +EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { @@ -1890,9 +1852,3 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, #include <linux/bpf_trace.h> EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); - -/* These are only used within the BPF_SYSCALL code */ -#ifdef CONFIG_BPF_SYSCALL -EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type); -EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu); -#endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index a4bb0b34375a..46f5f29605d4 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -19,6 +19,7 @@ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/ptr_ring.h> +#include <net/xdp.h> #include <linux/sched.h> #include <linux/workqueue.h> @@ -68,7 +69,7 @@ struct bpf_cpu_map { }; static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, - struct xdp_bulk_queue *bq); + struct xdp_bulk_queue *bq, bool in_napi_ctx); static u64 cpu_map_bitmap_size(const union bpf_attr *attr) { @@ -137,27 +138,6 @@ free_cmap: return ERR_PTR(err); } -static void __cpu_map_queue_destructor(void *ptr) -{ - /* The tear-down procedure should have made sure that queue is - * empty. See __cpu_map_entry_replace() and work-queue - * invoked cpu_map_kthread_stop(). Catch any broken behaviour - * gracefully and warn once. - */ - if (WARN_ON_ONCE(ptr)) - page_frag_free(ptr); -} - -static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) -{ - if (atomic_dec_and_test(&rcpu->refcnt)) { - /* The queue should be empty at this point */ - ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor); - kfree(rcpu->queue); - kfree(rcpu); - } -} - static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) { atomic_inc(&rcpu->refcnt); @@ -179,45 +159,8 @@ static void cpu_map_kthread_stop(struct work_struct *work) kthread_stop(rcpu->kthread); } -/* For now, xdp_pkt is a cpumap internal data structure, with info - * carried between enqueue to dequeue. It is mapped into the top - * headroom of the packet, to avoid allocating separate mem. - */ -struct xdp_pkt { - void *data; - u16 len; - u16 headroom; - u16 metasize; - struct net_device *dev_rx; -}; - -/* Convert xdp_buff to xdp_pkt */ -static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp) -{ - struct xdp_pkt *xdp_pkt; - int metasize; - int headroom; - - /* Assure headroom is available for storing info */ - headroom = xdp->data - xdp->data_hard_start; - metasize = xdp->data - xdp->data_meta; - metasize = metasize > 0 ? metasize : 0; - if (unlikely((headroom - metasize) < sizeof(*xdp_pkt))) - return NULL; - - /* Store info in top of packet */ - xdp_pkt = xdp->data_hard_start; - - xdp_pkt->data = xdp->data; - xdp_pkt->len = xdp->data_end - xdp->data; - xdp_pkt->headroom = headroom - sizeof(*xdp_pkt); - xdp_pkt->metasize = metasize; - - return xdp_pkt; -} - static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, - struct xdp_pkt *xdp_pkt) + struct xdp_frame *xdpf) { unsigned int frame_size; void *pkt_data_start; @@ -232,7 +175,7 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * would be preferred to set frame_size to 2048 or 4096 * depending on the driver. * frame_size = 2048; - * frame_len = frame_size - sizeof(*xdp_pkt); + * frame_len = frame_size - sizeof(*xdp_frame); * * Instead, with info avail, skb_shared_info in placed after * packet len. This, unfortunately fakes the truesize. @@ -240,21 +183,21 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * is not at a fixed memory location, with mixed length * packets, which is bad for cache-line hotness. */ - frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom + + frame_size = SKB_DATA_ALIGN(xdpf->len) + xdpf->headroom + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - pkt_data_start = xdp_pkt->data - xdp_pkt->headroom; + pkt_data_start = xdpf->data - xdpf->headroom; skb = build_skb(pkt_data_start, frame_size); if (!skb) return NULL; - skb_reserve(skb, xdp_pkt->headroom); - __skb_put(skb, xdp_pkt->len); - if (xdp_pkt->metasize) - skb_metadata_set(skb, xdp_pkt->metasize); + skb_reserve(skb, xdpf->headroom); + __skb_put(skb, xdpf->len); + if (xdpf->metasize) + skb_metadata_set(skb, xdpf->metasize); /* Essential SKB info: protocol and skb->dev */ - skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx); + skb->protocol = eth_type_trans(skb, xdpf->dev_rx); /* Optional SKB info, currently missing: * - HW checksum info (skb->ip_summed) @@ -265,6 +208,31 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, return skb; } +static void __cpu_map_ring_cleanup(struct ptr_ring *ring) +{ + /* The tear-down procedure should have made sure that queue is + * empty. See __cpu_map_entry_replace() and work-queue + * invoked cpu_map_kthread_stop(). Catch any broken behaviour + * gracefully and warn once. + */ + struct xdp_frame *xdpf; + + while ((xdpf = ptr_ring_consume(ring))) + if (WARN_ON_ONCE(xdpf)) + xdp_return_frame(xdpf); +} + +static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + if (atomic_dec_and_test(&rcpu->refcnt)) { + /* The queue should be empty at this point */ + __cpu_map_ring_cleanup(rcpu->queue); + ptr_ring_cleanup(rcpu->queue, NULL); + kfree(rcpu->queue); + kfree(rcpu); + } +} + static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; @@ -278,7 +246,7 @@ static int cpu_map_kthread_run(void *data) */ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { unsigned int processed = 0, drops = 0, sched = 0; - struct xdp_pkt *xdp_pkt; + struct xdp_frame *xdpf; /* Release CPU reschedule checks */ if (__ptr_ring_empty(rcpu->queue)) { @@ -301,13 +269,13 @@ static int cpu_map_kthread_run(void *data) * kthread CPU pinned. Lockless access to ptr_ring * consume side valid as no-resize allowed of queue. */ - while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) { + while ((xdpf = __ptr_ring_consume(rcpu->queue))) { struct sk_buff *skb; int ret; - skb = cpu_map_build_skb(rcpu, xdp_pkt); + skb = cpu_map_build_skb(rcpu, xdpf); if (!skb) { - page_frag_free(xdp_pkt); + xdp_return_frame(xdpf); continue; } @@ -407,7 +375,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu) struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); /* No concurrent bq_enqueue can run at this point */ - bq_flush_to_queue(rcpu, bq); + bq_flush_to_queue(rcpu, bq, false); } free_percpu(rcpu->bulkq); /* Cannot kthread_stop() here, last put free rcpu resources */ @@ -590,7 +558,7 @@ const struct bpf_map_ops cpu_map_ops = { }; static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, - struct xdp_bulk_queue *bq) + struct xdp_bulk_queue *bq, bool in_napi_ctx) { unsigned int processed = 0, drops = 0; const int to_cpu = rcpu->cpu; @@ -604,13 +572,16 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, spin_lock(&q->producer_lock); for (i = 0; i < bq->count; i++) { - void *xdp_pkt = bq->q[i]; + struct xdp_frame *xdpf = bq->q[i]; int err; - err = __ptr_ring_produce(q, xdp_pkt); + err = __ptr_ring_produce(q, xdpf); if (err) { drops++; - page_frag_free(xdp_pkt); /* Free xdp_pkt */ + if (likely(in_napi_ctx)) + xdp_return_frame_rx_napi(xdpf); + else + xdp_return_frame(xdpf); } processed++; } @@ -625,39 +596,39 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) +static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) - bq_flush_to_queue(rcpu, bq); + bq_flush_to_queue(rcpu, bq, true); /* Notice, xdp_buff/page MUST be queued here, long enough for * driver to code invoking us to finished, due to driver * (e.g. ixgbe) recycle tricks based on page-refcnt. * - * Thus, incoming xdp_pkt is always queued here (else we race + * Thus, incoming xdp_frame is always queued here (else we race * with another CPU on page-refcnt and remaining driver code). * Queue time is very short, as driver will invoke flush * operation, when completing napi->poll call. */ - bq->q[bq->count++] = xdp_pkt; + bq->q[bq->count++] = xdpf; return 0; } int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx) { - struct xdp_pkt *xdp_pkt; + struct xdp_frame *xdpf; - xdp_pkt = convert_to_xdp_pkt(xdp); - if (unlikely(!xdp_pkt)) + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) return -EOVERFLOW; /* Info needed when constructing SKB on remote CPU */ - xdp_pkt->dev_rx = dev_rx; + xdpf->dev_rx = dev_rx; - bq_enqueue(rcpu, xdp_pkt); + bq_enqueue(rcpu, xdpf); return 0; } @@ -693,7 +664,7 @@ void __cpu_map_flush(struct bpf_map *map) /* Flush all frames in bulkq to real queue */ bq = this_cpu_ptr(rcpu->bulkq); - bq_flush_to_queue(rcpu, bq); + bq_flush_to_queue(rcpu, bq, true); /* If already running, costs spin_lock_irqsave + smb_mb */ wake_up_process(rcpu->kthread); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 565f9ece9115..750d45edae79 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -48,15 +48,25 @@ * calls will fail at this point. */ #include <linux/bpf.h> +#include <net/xdp.h> #include <linux/filter.h> +#include <trace/events/xdp.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) +#define DEV_MAP_BULK_SIZE 16 +struct xdp_bulk_queue { + struct xdp_frame *q[DEV_MAP_BULK_SIZE]; + struct net_device *dev_rx; + unsigned int count; +}; + struct bpf_dtab_netdev { - struct net_device *dev; + struct net_device *dev; /* must be first member, due to tracepoint */ struct bpf_dtab *dtab; unsigned int bit; + struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; }; @@ -206,6 +216,54 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) __set_bit(bit, bitmap); } +static int bq_xmit_all(struct bpf_dtab_netdev *obj, + struct xdp_bulk_queue *bq, u32 flags, + bool in_napi_ctx) +{ + struct net_device *dev = obj->dev; + int sent = 0, drops = 0, err = 0; + int i; + + if (unlikely(!bq->count)) + return 0; + + for (i = 0; i < bq->count; i++) { + struct xdp_frame *xdpf = bq->q[i]; + + prefetch(xdpf); + } + + sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags); + if (sent < 0) { + err = sent; + sent = 0; + goto error; + } + drops = bq->count - sent; +out: + bq->count = 0; + + trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit, + sent, drops, bq->dev_rx, dev, err); + bq->dev_rx = NULL; + return 0; +error: + /* If ndo_xdp_xmit fails with an errno, no frames have been + * xmit'ed and it's our responsibility to them free all. + */ + for (i = 0; i < bq->count; i++) { + struct xdp_frame *xdpf = bq->q[i]; + + /* RX path under NAPI protection, can return frames faster */ + if (likely(in_napi_ctx)) + xdp_return_frame_rx_napi(xdpf); + else + xdp_return_frame(xdpf); + drops++; + } + goto out; +} + /* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled * from the driver before returning from its napi->poll() routine. The poll() * routine is called either from busy_poll context or net_rx_action signaled @@ -221,7 +279,7 @@ void __dev_map_flush(struct bpf_map *map) for_each_set_bit(bit, bitmap, map->max_entries) { struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]); - struct net_device *netdev; + struct xdp_bulk_queue *bq; /* This is possible if the dev entry is removed by user space * between xdp redirect and flush op. @@ -230,9 +288,9 @@ void __dev_map_flush(struct bpf_map *map) continue; __clear_bit(bit, bitmap); - netdev = dev->dev; - if (likely(netdev->netdev_ops->ndo_xdp_flush)) - netdev->netdev_ops->ndo_xdp_flush(netdev); + + bq = this_cpu_ptr(dev->bulkq); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true); } } @@ -240,37 +298,98 @@ void __dev_map_flush(struct bpf_map *map) * update happens in parallel here a dev_put wont happen until after reading the * ifindex. */ -struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) +struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct bpf_dtab_netdev *dev; + struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; - dev = READ_ONCE(dtab->netdev_map[key]); - return dev ? dev->dev : NULL; + obj = READ_ONCE(dtab->netdev_map[key]); + return obj; +} + +/* Runs under RCU-read-side, plus in softirq under NAPI protection. + * Thus, safe percpu variable access. + */ +static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, + struct net_device *dev_rx) + +{ + struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); + + if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) + bq_xmit_all(obj, bq, 0, true); + + /* Ingress dev_rx will be the same for all xdp_frame's in + * bulk_queue, because bq stored per-CPU and must be flushed + * from net_device drivers NAPI func end. + */ + if (!bq->dev_rx) + bq->dev_rx = dev_rx; + + bq->q[bq->count++] = xdpf; + return 0; +} + +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + struct net_device *dev = dst->dev; + struct xdp_frame *xdpf; + int err; + + if (!dev->netdev_ops->ndo_xdp_xmit) + return -EOPNOTSUPP; + + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) + return -EOVERFLOW; + + return bq_enqueue(dst, xdpf, dev_rx); +} + +int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + int err; + + err = xdp_ok_fwd_dev(dst->dev, skb->len); + if (unlikely(err)) + return err; + skb->dev = dst->dev; + generic_xdp_tx(skb, xdp_prog); + + return 0; } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { - struct net_device *dev = __dev_map_lookup_elem(map, *(u32 *)key); + struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); + struct net_device *dev = obj ? obj->dev : NULL; return dev ? &dev->ifindex : NULL; } static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { - if (dev->dev->netdev_ops->ndo_xdp_flush) { - struct net_device *fl = dev->dev; + if (dev->dev->netdev_ops->ndo_xdp_xmit) { + struct xdp_bulk_queue *bq; unsigned long *bitmap; + int cpu; for_each_online_cpu(cpu) { bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu); __clear_bit(dev->bit, bitmap); - fl->netdev_ops->ndo_xdp_flush(dev->dev); + bq = per_cpu_ptr(dev->bulkq, cpu); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false); } } } @@ -281,6 +400,7 @@ static void __dev_map_entry_free(struct rcu_head *rcu) dev = container_of(rcu, struct bpf_dtab_netdev, rcu); dev_map_flush_old(dev); + free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -313,6 +433,7 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct net *net = current->nsproxy->net_ns; + gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; struct bpf_dtab_netdev *dev, *old_dev; u32 i = *(u32 *)key; u32 ifindex = *(u32 *)value; @@ -327,13 +448,20 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (!ifindex) { dev = NULL; } else { - dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, - map->numa_node); + dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node); if (!dev) return -ENOMEM; + dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), + sizeof(void *), gfp); + if (!dev->bulkq) { + kfree(dev); + return -ENOMEM; + } + dev->dev = dev_get_by_index(net, ifindex); if (!dev->dev) { + free_percpu(dev->bulkq); kfree(dev); return -EINVAL; } @@ -405,6 +533,9 @@ static struct notifier_block dev_map_notifier = { static int __init dev_map_init(void) { + /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ + BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != + offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); return 0; } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b76828f23b49..513d9dfcf4ee 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -503,7 +503,9 @@ static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; - *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + @@ -530,7 +532,9 @@ static u32 htab_lru_map_gen_lookup(struct bpf_map *map, const int ret = BPF_REG_0; const int ref_reg = BPF_REG_1; - *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, offsetof(struct htab_elem, lru_node) + @@ -743,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, * old element will be freed immediately. * Otherwise return an error */ - atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); + l_new = ERR_PTR(-E2BIG); + goto dec_count; } l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); - if (!l_new) - return ERR_PTR(-ENOMEM); + if (!l_new) { + l_new = ERR_PTR(-ENOMEM); + goto dec_count; + } } memcpy(l_new->key, key, key_size); @@ -762,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, GFP_ATOMIC | __GFP_NOWARN); if (!pptr) { kfree(l_new); - return ERR_PTR(-ENOMEM); + l_new = ERR_PTR(-ENOMEM); + goto dec_count; } } @@ -776,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new->hash = hash; return l_new; +dec_count: + atomic_dec(&htab->count); + return l_new; } static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, @@ -1369,7 +1379,9 @@ static u32 htab_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; - *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3d24e238221e..73065e2d23c2 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -179,3 +179,18 @@ const struct bpf_func_proto bpf_get_current_comm_proto = { .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE, }; + +#ifdef CONFIG_CGROUPS +BPF_CALL_0(bpf_get_current_cgroup_id) +{ + struct cgroup *cgrp = task_dfl_cgroup(current); + + return cgrp->kn->id.id; +} + +const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { + .func = bpf_get_current_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; +#endif diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index bf6da59ae0d0..76efe9a183f5 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -150,8 +150,163 @@ static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) return 0; } +struct map_iter { + void *key; + bool done; +}; + +static struct map_iter *map_iter(struct seq_file *m) +{ + return m->private; +} + +static struct bpf_map *seq_file_to_map(struct seq_file *m) +{ + return file_inode(m->file)->i_private; +} + +static void map_iter_free(struct map_iter *iter) +{ + if (iter) { + kfree(iter->key); + kfree(iter); + } +} + +static struct map_iter *map_iter_alloc(struct bpf_map *map) +{ + struct map_iter *iter; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN); + if (!iter) + goto error; + + iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN); + if (!iter->key) + goto error; + + return iter; + +error: + map_iter_free(iter); + return NULL; +} + +static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct bpf_map *map = seq_file_to_map(m); + void *key = map_iter(m)->key; + + if (map_iter(m)->done) + return NULL; + + if (unlikely(v == SEQ_START_TOKEN)) + goto done; + + if (map->ops->map_get_next_key(map, key, key)) { + map_iter(m)->done = true; + return NULL; + } + +done: + ++(*pos); + return key; +} + +static void *map_seq_start(struct seq_file *m, loff_t *pos) +{ + if (map_iter(m)->done) + return NULL; + + return *pos ? map_iter(m)->key : SEQ_START_TOKEN; +} + +static void map_seq_stop(struct seq_file *m, void *v) +{ +} + +static int map_seq_show(struct seq_file *m, void *v) +{ + struct bpf_map *map = seq_file_to_map(m); + void *key = map_iter(m)->key; + + if (unlikely(v == SEQ_START_TOKEN)) { + seq_puts(m, "# WARNING!! The output is for debug purpose only\n"); + seq_puts(m, "# WARNING!! The output format will change\n"); + } else { + map->ops->map_seq_show_elem(map, key, m); + } + + return 0; +} + +static const struct seq_operations bpffs_map_seq_ops = { + .start = map_seq_start, + .next = map_seq_next, + .show = map_seq_show, + .stop = map_seq_stop, +}; + +static int bpffs_map_open(struct inode *inode, struct file *file) +{ + struct bpf_map *map = inode->i_private; + struct map_iter *iter; + struct seq_file *m; + int err; + + iter = map_iter_alloc(map); + if (!iter) + return -ENOMEM; + + err = seq_open(file, &bpffs_map_seq_ops); + if (err) { + map_iter_free(iter); + return err; + } + + m = file->private_data; + m->private = iter; + + return 0; +} + +static int bpffs_map_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + + map_iter_free(map_iter(m)); + + return seq_release(inode, file); +} + +/* bpffs_map_fops should only implement the basic + * read operation for a BPF map. The purpose is to + * provide a simple user intuitive way to do + * "cat bpffs/pathto/a-pinned-map". + * + * Other operations (e.g. write, lookup...) should be realized by + * the userspace tools (e.g. bpftool) through the + * BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update + * interface. + */ +static const struct file_operations bpffs_map_fops = { + .open = bpffs_map_open, + .read = seq_read, + .release = bpffs_map_release, +}; + +static int bpffs_obj_open(struct inode *inode, struct file *file) +{ + return -EIO; +} + +static const struct file_operations bpffs_obj_fops = { + .open = bpffs_obj_open, +}; + static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, - const struct inode_operations *iops) + const struct inode_operations *iops, + const struct file_operations *fops) { struct inode *dir = dentry->d_parent->d_inode; struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode); @@ -159,6 +314,7 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, return PTR_ERR(inode); inode->i_op = iops; + inode->i_fop = fops; inode->i_private = raw; bpf_dentry_finalize(dentry, inode, dir); @@ -167,12 +323,16 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg) { - return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops); + return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops, + &bpffs_obj_fops); } static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) { - return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops); + struct bpf_map *map = arg; + + return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops, + map->btf ? &bpffs_map_fops : &bpffs_obj_fops); } static struct dentry * @@ -279,13 +439,6 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname) ret = bpf_obj_do_pin(pname, raw, type); if (ret != 0) bpf_any_put(raw, type); - if ((trace_bpf_obj_pin_prog_enabled() || - trace_bpf_obj_pin_map_enabled()) && !ret) { - if (type == BPF_TYPE_PROG) - trace_bpf_obj_pin_prog(raw, ufd, pname); - if (type == BPF_TYPE_MAP) - trace_bpf_obj_pin_map(raw, ufd, pname); - } out: putname(pname); return ret; @@ -352,15 +505,8 @@ int bpf_obj_get_user(const char __user *pathname, int flags) else goto out; - if (ret < 0) { + if (ret < 0) bpf_any_put(raw, type); - } else if (trace_bpf_obj_get_prog_enabled() || - trace_bpf_obj_get_map_enabled()) { - if (type == BPF_TYPE_PROG) - trace_bpf_obj_get_prog(raw, ret, pname); - if (type == BPF_TYPE_MAP) - trace_bpf_obj_get_map(raw, ret, pname); - } out: putname(pname); return ret; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index b4b5b81e7251..1603492c9cc7 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -623,8 +623,9 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) if (!key || key->prefixlen > trie->max_prefixlen) goto find_leftmost; - node_stack = kmalloc(trie->max_prefixlen * sizeof(struct lpm_trie_node *), - GFP_ATOMIC | __GFP_NOWARN); + node_stack = kmalloc_array(trie->max_prefixlen, + sizeof(struct lpm_trie_node *), + GFP_ATOMIC | __GFP_NOWARN); if (!node_stack) return -ENOMEM; diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index c9401075b58c..ac747d5cf7c6 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -474,8 +474,10 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map) struct bpf_prog_offload *offload; bool ret; - if (!bpf_prog_is_dev_bound(prog->aux) || !bpf_map_is_dev_bound(map)) + if (!bpf_prog_is_dev_bound(prog->aux)) return false; + if (!bpf_map_is_dev_bound(map)) + return bpf_map_offload_neutral(map); down_read(&bpf_devs_lock); offload = prog->aux->offload; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 95a84b2f10ce..c4d75c52b4fc 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -48,14 +48,41 @@ #define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) -struct bpf_stab { - struct bpf_map map; - struct sock **sock_map; +struct bpf_sock_progs { struct bpf_prog *bpf_tx_msg; struct bpf_prog *bpf_parse; struct bpf_prog *bpf_verdict; }; +struct bpf_stab { + struct bpf_map map; + struct sock **sock_map; + struct bpf_sock_progs progs; +}; + +struct bucket { + struct hlist_head head; + raw_spinlock_t lock; +}; + +struct bpf_htab { + struct bpf_map map; + struct bucket *buckets; + atomic_t count; + u32 n_buckets; + u32 elem_size; + struct bpf_sock_progs progs; + struct rcu_head rcu; +}; + +struct htab_elem { + struct rcu_head rcu; + struct hlist_node hash_node; + u32 hash; + struct sock *sk; + char key[0]; +}; + enum smap_psock_state { SMAP_TX_RUNNING, }; @@ -63,6 +90,8 @@ enum smap_psock_state { struct smap_psock_map_entry { struct list_head list; struct sock **entry; + struct htab_elem __rcu *hash_link; + struct bpf_htab __rcu *htab; }; struct smap_psock { @@ -92,6 +121,7 @@ struct smap_psock { struct bpf_prog *bpf_parse; struct bpf_prog *bpf_verdict; struct list_head maps; + spinlock_t maps_lock; /* Back reference used when sock callback trigger sockmap operations */ struct sock *sock; @@ -112,6 +142,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); static int bpf_tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +static void bpf_tcp_close(struct sock *sk, long timeout); static inline struct smap_psock *smap_psock_sk(const struct sock *sk) { @@ -133,7 +164,42 @@ out: return !empty; } -static struct proto tcp_bpf_proto; +enum { + SOCKMAP_IPV4, + SOCKMAP_IPV6, + SOCKMAP_NUM_PROTS, +}; + +enum { + SOCKMAP_BASE, + SOCKMAP_TX, + SOCKMAP_NUM_CONFIGS, +}; + +static struct proto *saved_tcpv6_prot __read_mostly; +static DEFINE_SPINLOCK(tcpv6_prot_lock); +static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS]; +static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS], + struct proto *base) +{ + prot[SOCKMAP_BASE] = *base; + prot[SOCKMAP_BASE].close = bpf_tcp_close; + prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg; + prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read; + + prot[SOCKMAP_TX] = prot[SOCKMAP_BASE]; + prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg; + prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage; +} + +static void update_sk_prot(struct sock *sk, struct smap_psock *psock) +{ + int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4; + int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE; + + sk->sk_prot = &bpf_tcp_prots[family][conf]; +} + static int bpf_tcp_init(struct sock *sk) { struct smap_psock *psock; @@ -153,14 +219,17 @@ static int bpf_tcp_init(struct sock *sk) psock->save_close = sk->sk_prot->close; psock->sk_proto = sk->sk_prot; - if (psock->bpf_tx_msg) { - tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg; - tcp_bpf_proto.sendpage = bpf_tcp_sendpage; - tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg; - tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read; + /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */ + if (sk->sk_family == AF_INET6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + spin_lock_bh(&tcpv6_prot_lock); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + spin_unlock_bh(&tcpv6_prot_lock); } - - sk->sk_prot = &tcp_bpf_proto; + update_sk_prot(sk, psock); rcu_read_unlock(); return 0; } @@ -191,18 +260,64 @@ out: rcu_read_unlock(); } +static struct htab_elem *lookup_elem_raw(struct hlist_head *head, + u32 hash, void *key, u32 key_size) +{ + struct htab_elem *l; + + hlist_for_each_entry_rcu(l, head, hash_node) { + if (l->hash == hash && !memcmp(&l->key, key, key_size)) + return l; + } + + return NULL; +} + +static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &htab->buckets[hash & (htab->n_buckets - 1)]; +} + +static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &__select_bucket(htab, hash)->head; +} + +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +{ + atomic_dec(&htab->count); + kfree_rcu(l, rcu); +} + +static struct smap_psock_map_entry *psock_map_pop(struct sock *sk, + struct smap_psock *psock) +{ + struct smap_psock_map_entry *e; + + spin_lock_bh(&psock->maps_lock); + e = list_first_entry_or_null(&psock->maps, + struct smap_psock_map_entry, + list); + if (e) + list_del(&e->list); + spin_unlock_bh(&psock->maps_lock); + return e; +} + static void bpf_tcp_close(struct sock *sk, long timeout) { void (*close_fun)(struct sock *sk, long timeout); - struct smap_psock_map_entry *e, *tmp; + struct smap_psock_map_entry *e; struct sk_msg_buff *md, *mtmp; struct smap_psock *psock; struct sock *osk; + lock_sock(sk); rcu_read_lock(); psock = smap_psock_sk(sk); if (unlikely(!psock)) { rcu_read_unlock(); + release_sock(sk); return sk->sk_prot->close(sk, timeout); } @@ -213,7 +328,6 @@ static void bpf_tcp_close(struct sock *sk, long timeout) */ close_fun = psock->save_close; - write_lock_bh(&sk->sk_callback_lock); if (psock->cork) { free_start_sg(psock->sock, psock->cork); kfree(psock->cork); @@ -226,15 +340,40 @@ static void bpf_tcp_close(struct sock *sk, long timeout) kfree(md); } - list_for_each_entry_safe(e, tmp, &psock->maps, list) { - osk = cmpxchg(e->entry, sk, NULL); - if (osk == sk) { - list_del(&e->list); - smap_release_sock(psock, sk); + e = psock_map_pop(sk, psock); + while (e) { + if (e->entry) { + osk = cmpxchg(e->entry, sk, NULL); + if (osk == sk) { + smap_release_sock(psock, sk); + } + } else { + struct htab_elem *link = rcu_dereference(e->hash_link); + struct bpf_htab *htab = rcu_dereference(e->htab); + struct hlist_head *head; + struct htab_elem *l; + struct bucket *b; + + b = __select_bucket(htab, link->hash); + head = &b->head; + raw_spin_lock_bh(&b->lock); + l = lookup_elem_raw(head, + link->hash, link->key, + htab->map.key_size); + /* If another thread deleted this object skip deletion. + * The refcnt on psock may or may not be zero. + */ + if (l) { + hlist_del_rcu(&link->hash_node); + smap_release_sock(psock, link->sk); + free_htab_elem(htab, link); + } + raw_spin_unlock_bh(&b->lock); } + e = psock_map_pop(sk, psock); } - write_unlock_bh(&sk->sk_callback_lock); rcu_read_unlock(); + release_sock(sk); close_fun(sk, timeout); } @@ -432,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) while (sg[i].length) { free += sg[i].length; sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); + if (!md->skb) + put_page(sg_page(&sg[i])); sg[i].length = 0; sg[i].page_link = 0; sg[i].offset = 0; @@ -441,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) if (i == MAX_SKB_FRAGS) i = 0; } + if (md->skb) + consume_skb(md->skb); return free; } @@ -461,7 +603,7 @@ static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md) static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md) { return ((_rc == SK_PASS) ? - (md->map ? __SK_REDIRECT : __SK_PASS) : + (md->sk_redir ? __SK_REDIRECT : __SK_PASS) : __SK_DROP); } @@ -483,6 +625,7 @@ static unsigned int smap_do_tx_msg(struct sock *sk, } bpf_compute_data_pointers_sg(md); + md->sk = sk; rc = (*prog->bpf_func)(md, prog->insnsi); psock->apply_bytes = md->apply_bytes; @@ -905,12 +1048,12 @@ static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); while (msg_data_left(msg)) { - struct sk_msg_buff *m; + struct sk_msg_buff *m = NULL; bool enospc = false; int copy; if (sk->sk_err) { - err = sk->sk_err; + err = -sk->sk_err; goto out_err; } @@ -973,8 +1116,11 @@ wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: err = sk_stream_wait_memory(sk, &timeo); - if (err) + if (err) { + if (m && m != psock->cork) + free_start_sg(sk, m); goto out_err; + } } out_err: if (err < 0) @@ -1070,8 +1216,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock, static int bpf_tcp_ulp_register(void) { - tcp_bpf_proto = tcp_prot; - tcp_bpf_proto.close = bpf_tcp_close; + build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot); /* Once BPF TX ULP is registered it is never unregistered. It * will be in the ULP list for the lifetime of the system. Doing * duplicate registers is not a problem. @@ -1092,9 +1237,9 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) * when we orphan the skb so that we don't have the possibility * to reference a stale map. */ - TCP_SKB_CB(skb)->bpf.map = NULL; + TCP_SKB_CB(skb)->bpf.sk_redir = NULL; skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); preempt_enable(); @@ -1102,7 +1247,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) /* Moving return codes from UAPI namespace into internal namespace */ return rc == SK_PASS ? - (TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) : + (TCP_SKB_CB(skb)->bpf.sk_redir ? __SK_REDIRECT : __SK_PASS) : __SK_DROP; } @@ -1316,7 +1461,9 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock) { if (refcount_dec_and_test(&psock->refcnt)) { tcp_cleanup_ulp(sock); + write_lock_bh(&sock->sk_callback_lock); smap_stop_sock(psock, sock); + write_unlock_bh(&sock->sk_callback_lock); clear_bit(SMAP_TX_RUNNING, &psock->state); rcu_assign_sk_user_data(sock, NULL); call_rcu_sched(&psock->rcu, smap_destroy_psock); @@ -1347,7 +1494,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); @@ -1372,7 +1519,6 @@ static int smap_init_sock(struct smap_psock *psock, } static void smap_init_progs(struct smap_psock *psock, - struct bpf_stab *stab, struct bpf_prog *verdict, struct bpf_prog *parse) { @@ -1450,14 +1596,13 @@ static void smap_gc_work(struct work_struct *w) kfree(psock); } -static struct smap_psock *smap_init_psock(struct sock *sock, - struct bpf_stab *stab) +static struct smap_psock *smap_init_psock(struct sock *sock, int node) { struct smap_psock *psock; psock = kzalloc_node(sizeof(struct smap_psock), GFP_ATOMIC | __GFP_NOWARN, - stab->map.numa_node); + node); if (!psock) return ERR_PTR(-ENOMEM); @@ -1469,6 +1614,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock, INIT_LIST_HEAD(&psock->maps); INIT_LIST_HEAD(&psock->ingress); refcount_set(&psock->refcnt, 1); + spin_lock_init(&psock->maps_lock); rcu_assign_sk_user_data(sock, psock); sock_hold(sock); @@ -1525,16 +1671,32 @@ free_stab: return ERR_PTR(err); } -static void smap_list_remove(struct smap_psock *psock, struct sock **entry) +static void smap_list_map_remove(struct smap_psock *psock, + struct sock **entry) { struct smap_psock_map_entry *e, *tmp; + spin_lock_bh(&psock->maps_lock); list_for_each_entry_safe(e, tmp, &psock->maps, list) { - if (e->entry == entry) { + if (e->entry == entry) + list_del(&e->list); + } + spin_unlock_bh(&psock->maps_lock); +} + +static void smap_list_hash_remove(struct smap_psock *psock, + struct htab_elem *hash_link) +{ + struct smap_psock_map_entry *e, *tmp; + + spin_lock_bh(&psock->maps_lock); + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + struct htab_elem *c = rcu_dereference(e->hash_link); + + if (c == hash_link) list_del(&e->list); - break; - } } + spin_unlock_bh(&psock->maps_lock); } static void sock_map_free(struct bpf_map *map) @@ -1560,7 +1722,6 @@ static void sock_map_free(struct bpf_map *map) if (!sock) continue; - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* This check handles a racing sock event that can get the * sk_callback_lock before this case but after xchg happens @@ -1568,10 +1729,9 @@ static void sock_map_free(struct bpf_map *map) * to be null and queued for garbage collection. */ if (likely(psock)) { - smap_list_remove(psock, &stab->sock_map[i]); + smap_list_map_remove(psock, &stab->sock_map[i]); smap_release_sock(psock, sock); } - write_unlock_bh(&sock->sk_callback_lock); } rcu_read_unlock(); @@ -1620,17 +1780,15 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key) if (!sock) return -EINVAL; - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); if (!psock) goto out; if (psock->bpf_parse) smap_stop_sock(psock, sock); - smap_list_remove(psock, &stab->sock_map[k]); + smap_list_map_remove(psock, &stab->sock_map[k]); smap_release_sock(psock, sock); out: - write_unlock_bh(&sock->sk_callback_lock); return 0; } @@ -1662,40 +1820,26 @@ out: * - sock_map must use READ_ONCE and (cmp)xchg operations * - BPF verdict/parse programs must use READ_ONCE and xchg operations */ -static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, - struct bpf_map *map, - void *key, u64 flags) + +static int __sock_map_ctx_update_elem(struct bpf_map *map, + struct bpf_sock_progs *progs, + struct sock *sock, + struct sock **map_link, + void *key) { - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - struct smap_psock_map_entry *e = NULL; struct bpf_prog *verdict, *parse, *tx_msg; - struct sock *osock, *sock; + struct smap_psock_map_entry *e = NULL; struct smap_psock *psock; - u32 i = *(u32 *)key; bool new = false; - int err; - - if (unlikely(flags > BPF_EXIST)) - return -EINVAL; - - if (unlikely(i >= stab->map.max_entries)) - return -E2BIG; - - sock = READ_ONCE(stab->sock_map[i]); - if (flags == BPF_EXIST && !sock) - return -ENOENT; - else if (flags == BPF_NOEXIST && sock) - return -EEXIST; - - sock = skops->sk; + int err = 0; /* 1. If sock map has BPF programs those will be inherited by the * sock being added. If the sock is already attached to BPF programs * this results in an error. */ - verdict = READ_ONCE(stab->bpf_verdict); - parse = READ_ONCE(stab->bpf_parse); - tx_msg = READ_ONCE(stab->bpf_tx_msg); + verdict = READ_ONCE(progs->bpf_verdict); + parse = READ_ONCE(progs->bpf_parse); + tx_msg = READ_ONCE(progs->bpf_tx_msg); if (parse && verdict) { /* bpf prog refcnt may be zero if a concurrent attach operation @@ -1725,7 +1869,6 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, } } - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* 2. Do not allow inheriting programs if psock exists and has @@ -1748,7 +1891,7 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, goto out_progs; } } else { - psock = smap_init_psock(sock, stab); + psock = smap_init_psock(sock, map->numa_node); if (IS_ERR(psock)) { err = PTR_ERR(psock); goto out_progs; @@ -1758,12 +1901,13 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, new = true; } - e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); - if (!e) { - err = -ENOMEM; - goto out_progs; + if (map_link) { + e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); + if (!e) { + err = -ENOMEM; + goto out_free; + } } - e->entry = &stab->sock_map[i]; /* 3. At this point we have a reference to a valid psock that is * running. Attach any BPF programs needed. @@ -1780,8 +1924,10 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, err = smap_init_sock(psock, sock); if (err) goto out_free; - smap_init_progs(psock, stab, verdict, parse); + smap_init_progs(psock, verdict, parse); + write_lock_bh(&sock->sk_callback_lock); smap_start_sock(psock, sock); + write_unlock_bh(&sock->sk_callback_lock); } /* 4. Place psock in sockmap for use and stop any programs on @@ -1789,19 +1935,13 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, * it with. Because we can only have a single set of programs if * old_sock has a strp we can stop it. */ - list_add_tail(&e->list, &psock->maps); - write_unlock_bh(&sock->sk_callback_lock); - - osock = xchg(&stab->sock_map[i], sock); - if (osock) { - struct smap_psock *opsock = smap_psock_sk(osock); - - write_lock_bh(&osock->sk_callback_lock); - smap_list_remove(opsock, &stab->sock_map[i]); - smap_release_sock(opsock, osock); - write_unlock_bh(&osock->sk_callback_lock); + if (map_link) { + e->entry = map_link; + spin_lock_bh(&psock->maps_lock); + list_add_tail(&e->list, &psock->maps); + spin_unlock_bh(&psock->maps_lock); } - return 0; + return err; out_free: smap_release_sock(psock, sock); out_progs: @@ -1811,28 +1951,75 @@ out_progs: } if (tx_msg) bpf_prog_put(tx_msg); - write_unlock_bh(&sock->sk_callback_lock); kfree(e); return err; } -int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) +static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, + struct bpf_map *map, + void *key, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct bpf_sock_progs *progs = &stab->progs; + struct sock *osock, *sock; + u32 i = *(u32 *)key; + int err; + + if (unlikely(flags > BPF_EXIST)) + return -EINVAL; + + if (unlikely(i >= stab->map.max_entries)) + return -E2BIG; + + sock = READ_ONCE(stab->sock_map[i]); + if (flags == BPF_EXIST && !sock) + return -ENOENT; + else if (flags == BPF_NOEXIST && sock) + return -EEXIST; + + sock = skops->sk; + err = __sock_map_ctx_update_elem(map, progs, sock, &stab->sock_map[i], + key); + if (err) + goto out; + + osock = xchg(&stab->sock_map[i], sock); + if (osock) { + struct smap_psock *opsock = smap_psock_sk(osock); + + smap_list_map_remove(opsock, &stab->sock_map[i]); + smap_release_sock(opsock, osock); + } +out: + return err; +} + +int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) +{ + struct bpf_sock_progs *progs; struct bpf_prog *orig; - if (unlikely(map->map_type != BPF_MAP_TYPE_SOCKMAP)) + if (map->map_type == BPF_MAP_TYPE_SOCKMAP) { + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + + progs = &stab->progs; + } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH) { + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + progs = &htab->progs; + } else { return -EINVAL; + } switch (type) { case BPF_SK_MSG_VERDICT: - orig = xchg(&stab->bpf_tx_msg, prog); + orig = xchg(&progs->bpf_tx_msg, prog); break; case BPF_SK_SKB_STREAM_PARSER: - orig = xchg(&stab->bpf_parse, prog); + orig = xchg(&progs->bpf_parse, prog); break; case BPF_SK_SKB_STREAM_VERDICT: - orig = xchg(&stab->bpf_verdict, prog); + orig = xchg(&progs->bpf_verdict, prog); break; default: return -EOPNOTSUPP; @@ -1844,6 +2031,24 @@ int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) return 0; } +int sockmap_get_from_fd(const union bpf_attr *attr, int type, + struct bpf_prog *prog) +{ + int ufd = attr->target_fd; + struct bpf_map *map; + struct fd f; + int err; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = sock_map_prog(map, prog, attr->attach_type); + fdput(f); + return err; +} + static void *sock_map_lookup(struct bpf_map *map, void *key) { return NULL; @@ -1873,28 +2078,421 @@ static int sock_map_update_elem(struct bpf_map *map, return -EOPNOTSUPP; } + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); err = sock_map_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); fput(socket->file); return err; } static void sock_map_release(struct bpf_map *map) { - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct bpf_sock_progs *progs; struct bpf_prog *orig; - orig = xchg(&stab->bpf_parse, NULL); + if (map->map_type == BPF_MAP_TYPE_SOCKMAP) { + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + + progs = &stab->progs; + } else { + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + progs = &htab->progs; + } + + orig = xchg(&progs->bpf_parse, NULL); if (orig) bpf_prog_put(orig); - orig = xchg(&stab->bpf_verdict, NULL); + orig = xchg(&progs->bpf_verdict, NULL); if (orig) bpf_prog_put(orig); - orig = xchg(&stab->bpf_tx_msg, NULL); + orig = xchg(&progs->bpf_tx_msg, NULL); if (orig) bpf_prog_put(orig); } +static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) +{ + struct bpf_htab *htab; + int i, err; + u64 cost; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->value_size != 4 || + attr->map_flags & ~SOCK_CREATE_FLAG_MASK) + return ERR_PTR(-EINVAL); + + if (attr->key_size > MAX_BPF_STACK) + /* eBPF programs initialize keys on stack, so they cannot be + * larger than max stack size + */ + return ERR_PTR(-E2BIG); + + err = bpf_tcp_ulp_register(); + if (err && err != -EEXIST) + return ERR_PTR(err); + + htab = kzalloc(sizeof(*htab), GFP_USER); + if (!htab) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&htab->map, attr); + + htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); + htab->elem_size = sizeof(struct htab_elem) + + round_up(htab->map.key_size, 8); + err = -EINVAL; + if (htab->n_buckets == 0 || + htab->n_buckets > U32_MAX / sizeof(struct bucket)) + goto free_htab; + + cost = (u64) htab->n_buckets * sizeof(struct bucket) + + (u64) htab->elem_size * htab->map.max_entries; + + if (cost >= U32_MAX - PAGE_SIZE) + goto free_htab; + + htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + err = bpf_map_precharge_memlock(htab->map.pages); + if (err) + goto free_htab; + + err = -ENOMEM; + htab->buckets = bpf_map_area_alloc( + htab->n_buckets * sizeof(struct bucket), + htab->map.numa_node); + if (!htab->buckets) + goto free_htab; + + for (i = 0; i < htab->n_buckets; i++) { + INIT_HLIST_HEAD(&htab->buckets[i].head); + raw_spin_lock_init(&htab->buckets[i].lock); + } + + return &htab->map; +free_htab: + kfree(htab); + return ERR_PTR(err); +} + +static void __bpf_htab_free(struct rcu_head *rcu) +{ + struct bpf_htab *htab; + + htab = container_of(rcu, struct bpf_htab, rcu); + bpf_map_area_free(htab->buckets); + kfree(htab); +} + +static void sock_hash_free(struct bpf_map *map) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + int i; + + synchronize_rcu(); + + /* At this point no update, lookup or delete operations can happen. + * However, be aware we can still get a socket state event updates, + * and data ready callabacks that reference the psock from sk_user_data + * Also psock worker threads are still in-flight. So smap_release_sock + * will only free the psock after cancel_sync on the worker threads + * and a grace period expire to ensure psock is really safe to remove. + */ + rcu_read_lock(); + for (i = 0; i < htab->n_buckets; i++) { + struct bucket *b = __select_bucket(htab, i); + struct hlist_head *head; + struct hlist_node *n; + struct htab_elem *l; + + raw_spin_lock_bh(&b->lock); + head = &b->head; + hlist_for_each_entry_safe(l, n, head, hash_node) { + struct sock *sock = l->sk; + struct smap_psock *psock; + + hlist_del_rcu(&l->hash_node); + psock = smap_psock_sk(sock); + /* This check handles a racing sock event that can get + * the sk_callback_lock before this case but after xchg + * causing the refcnt to hit zero and sock user data + * (psock) to be null and queued for garbage collection. + */ + if (likely(psock)) { + smap_list_hash_remove(psock, l); + smap_release_sock(psock, sock); + } + free_htab_elem(htab, l); + } + raw_spin_unlock_bh(&b->lock); + } + rcu_read_unlock(); + call_rcu(&htab->rcu, __bpf_htab_free); +} + +static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, + void *key, u32 key_size, u32 hash, + struct sock *sk, + struct htab_elem *old_elem) +{ + struct htab_elem *l_new; + + if (atomic_inc_return(&htab->count) > htab->map.max_entries) { + if (!old_elem) { + atomic_dec(&htab->count); + return ERR_PTR(-E2BIG); + } + } + l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, + htab->map.numa_node); + if (!l_new) + return ERR_PTR(-ENOMEM); + + memcpy(l_new->key, key, key_size); + l_new->sk = sk; + l_new->hash = hash; + return l_new; +} + +static inline u32 htab_map_hash(const void *key, u32 key_len) +{ + return jhash(key, key_len, 0); +} + +static int sock_hash_get_next_key(struct bpf_map *map, + void *key, void *next_key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct htab_elem *l, *next_l; + struct hlist_head *h; + u32 hash, key_size; + int i = 0; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + key_size = map->key_size; + if (!key) + goto find_first_elem; + hash = htab_map_hash(key, key_size); + h = select_bucket(htab, hash); + + l = lookup_elem_raw(h, hash, key, key_size); + if (!l) + goto find_first_elem; + next_l = hlist_entry_safe( + rcu_dereference_raw(hlist_next_rcu(&l->hash_node)), + struct htab_elem, hash_node); + if (next_l) { + memcpy(next_key, next_l->key, key_size); + return 0; + } + + /* no more elements in this hash list, go to the next bucket */ + i = hash & (htab->n_buckets - 1); + i++; + +find_first_elem: + /* iterate over buckets */ + for (; i < htab->n_buckets; i++) { + h = select_bucket(htab, i); + + /* pick first element in the bucket */ + next_l = hlist_entry_safe( + rcu_dereference_raw(hlist_first_rcu(h)), + struct htab_elem, hash_node); + if (next_l) { + /* if it's not empty, just return it */ + memcpy(next_key, next_l->key, key_size); + return 0; + } + } + + /* iterated over all buckets and all elements */ + return -ENOENT; +} + +static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, + struct bpf_map *map, + void *key, u64 map_flags) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct bpf_sock_progs *progs = &htab->progs; + struct htab_elem *l_new = NULL, *l_old; + struct smap_psock_map_entry *e = NULL; + struct hlist_head *head; + struct smap_psock *psock; + u32 key_size, hash; + struct sock *sock; + struct bucket *b; + int err; + + sock = skops->sk; + + if (sock->sk_type != SOCK_STREAM || + sock->sk_protocol != IPPROTO_TCP) + return -EOPNOTSUPP; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + + e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); + if (!e) + return -ENOMEM; + + WARN_ON_ONCE(!rcu_read_lock_held()); + key_size = map->key_size; + hash = htab_map_hash(key, key_size); + b = __select_bucket(htab, hash); + head = &b->head; + + err = __sock_map_ctx_update_elem(map, progs, sock, NULL, key); + if (err) + goto err; + + /* psock is valid here because otherwise above *ctx_update_elem would + * have thrown an error. It is safe to skip error check. + */ + psock = smap_psock_sk(sock); + raw_spin_lock_bh(&b->lock); + l_old = lookup_elem_raw(head, hash, key, key_size); + if (l_old && map_flags == BPF_NOEXIST) { + err = -EEXIST; + goto bucket_err; + } + if (!l_old && map_flags == BPF_EXIST) { + err = -ENOENT; + goto bucket_err; + } + + l_new = alloc_sock_hash_elem(htab, key, key_size, hash, sock, l_old); + if (IS_ERR(l_new)) { + err = PTR_ERR(l_new); + goto bucket_err; + } + + rcu_assign_pointer(e->hash_link, l_new); + rcu_assign_pointer(e->htab, + container_of(map, struct bpf_htab, map)); + spin_lock_bh(&psock->maps_lock); + list_add_tail(&e->list, &psock->maps); + spin_unlock_bh(&psock->maps_lock); + + /* add new element to the head of the list, so that + * concurrent search will find it before old elem + */ + hlist_add_head_rcu(&l_new->hash_node, head); + if (l_old) { + psock = smap_psock_sk(l_old->sk); + + hlist_del_rcu(&l_old->hash_node); + smap_list_hash_remove(psock, l_old); + smap_release_sock(psock, l_old->sk); + free_htab_elem(htab, l_old); + } + raw_spin_unlock_bh(&b->lock); + return 0; +bucket_err: + smap_release_sock(psock, sock); + raw_spin_unlock_bh(&b->lock); +err: + kfree(e); + return err; +} + +static int sock_hash_update_elem(struct bpf_map *map, + void *key, void *value, u64 flags) +{ + struct bpf_sock_ops_kern skops; + u32 fd = *(u32 *)value; + struct socket *socket; + int err; + + socket = sockfd_lookup(fd, &err); + if (!socket) + return err; + + skops.sk = socket->sk; + if (!skops.sk) { + fput(socket->file); + return -EINVAL; + } + + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); + err = sock_hash_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); + fput(socket->file); + return err; +} + +static int sock_hash_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_head *head; + struct bucket *b; + struct htab_elem *l; + u32 hash, key_size; + int ret = -ENOENT; + + key_size = map->key_size; + hash = htab_map_hash(key, key_size); + b = __select_bucket(htab, hash); + head = &b->head; + + raw_spin_lock_bh(&b->lock); + l = lookup_elem_raw(head, hash, key, key_size); + if (l) { + struct sock *sock = l->sk; + struct smap_psock *psock; + + hlist_del_rcu(&l->hash_node); + psock = smap_psock_sk(sock); + /* This check handles a racing sock event that can get the + * sk_callback_lock before this case but after xchg happens + * causing the refcnt to hit zero and sock user data (psock) + * to be null and queued for garbage collection. + */ + if (likely(psock)) { + smap_list_hash_remove(psock, l); + smap_release_sock(psock, sock); + } + free_htab_elem(htab, l); + ret = 0; + } + raw_spin_unlock_bh(&b->lock); + return ret; +} + +struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_head *head; + struct htab_elem *l; + u32 key_size, hash; + struct bucket *b; + struct sock *sk; + + key_size = map->key_size; + hash = htab_map_hash(key, key_size); + b = __select_bucket(htab, hash); + head = &b->head; + + l = lookup_elem_raw(head, hash, key, key_size); + sk = l ? l->sk : NULL; + return sk; +} + const struct bpf_map_ops sock_map_ops = { .map_alloc = sock_map_alloc, .map_free = sock_map_free, @@ -1905,6 +2503,16 @@ const struct bpf_map_ops sock_map_ops = { .map_release_uref = sock_map_release, }; +const struct bpf_map_ops sock_hash_ops = { + .map_alloc = sock_hash_alloc, + .map_free = sock_hash_free, + .map_lookup_elem = sock_map_lookup, + .map_get_next_key = sock_hash_get_next_key, + .map_update_elem = sock_hash_update_elem, + .map_delete_elem = sock_hash_delete_elem, + .map_release_uref = sock_map_release, +}; + BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, struct bpf_map *, map, void *, key, u64, flags) { @@ -1922,3 +2530,21 @@ const struct bpf_func_proto bpf_sock_map_update_proto = { .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; + +BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock, + struct bpf_map *, map, void *, key, u64, flags) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return sock_hash_ctx_update_elem(bpf_sock, map, key, flags); +} + +const struct bpf_func_proto bpf_sock_hash_update_proto = { + .func = bpf_sock_hash_update, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 57eeb1234b67..b675a3f3d141 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -11,6 +11,7 @@ #include <linux/perf_event.h> #include <linux/elf.h> #include <linux/pagemap.h> +#include <linux/irq_work.h> #include "percpu_freelist.h" #define STACK_CREATE_FLAG_MASK \ @@ -32,6 +33,23 @@ struct bpf_stack_map { struct stack_map_bucket *buckets[]; }; +/* irq_work to run up_read() for build_id lookup in nmi context */ +struct stack_map_irq_work { + struct irq_work irq_work; + struct rw_semaphore *sem; +}; + +static void do_up_read(struct irq_work *entry) +{ + struct stack_map_irq_work *work; + + work = container_of(entry, struct stack_map_irq_work, irq_work); + up_read(work->sem); + work->sem = NULL; +} + +static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work); + static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); @@ -262,27 +280,31 @@ out: return ret; } -static void stack_map_get_build_id_offset(struct bpf_map *map, - struct stack_map_bucket *bucket, +static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, u64 *ips, u32 trace_nr, bool user) { int i; struct vm_area_struct *vma; - struct bpf_stack_build_id *id_offs; - - bucket->nr = trace_nr; - id_offs = (struct bpf_stack_build_id *)bucket->data; + bool irq_work_busy = false; + struct stack_map_irq_work *work = NULL; + + if (in_nmi()) { + work = this_cpu_ptr(&up_read_work); + if (work->irq_work.flags & IRQ_WORK_BUSY) + /* cannot queue more up_read, fallback */ + irq_work_busy = true; + } /* - * We cannot do up_read() in nmi context, so build_id lookup is - * only supported for non-nmi events. If at some point, it is - * possible to run find_vma() without taking the semaphore, we - * would like to allow build_id lookup in nmi context. + * We cannot do up_read() in nmi context. To do build_id lookup + * in nmi context, we need to run up_read() in irq_work. We use + * a percpu variable to do the irq_work. If the irq_work is + * already used by another lookup, we fall back to report ips. * * Same fallback is used for kernel stack (!user) on a stackmap * with build_id. */ - if (!user || !current || !current->mm || in_nmi() || + if (!user || !current || !current->mm || irq_work_busy || down_read_trylock(¤t->mm->mmap_sem) == 0) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { @@ -304,7 +326,13 @@ static void stack_map_get_build_id_offset(struct bpf_map *map, - vma->vm_start; id_offs[i].status = BPF_STACK_BUILD_ID_VALID; } - up_read(¤t->mm->mmap_sem); + + if (!work) { + up_read(¤t->mm->mmap_sem); + } else { + work->sem = ¤t->mm->mmap_sem; + irq_work_queue(&work->irq_work); + } } BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, @@ -361,8 +389,10 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; - stack_map_get_build_id_offset(map, new_bucket, ips, - trace_nr, user); + new_bucket->nr = trace_nr; + stack_map_get_build_id_offset( + (struct bpf_stack_build_id *)new_bucket->data, + ips, trace_nr, user); trace_len = trace_nr * sizeof(struct bpf_stack_build_id); if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, new_bucket->data, trace_len) == 0) { @@ -405,6 +435,73 @@ const struct bpf_func_proto bpf_get_stackid_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size, + u64, flags) +{ + u32 init_nr, trace_nr, copy_len, elem_size, num_elem; + bool user_build_id = flags & BPF_F_USER_BUILD_ID; + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + bool user = flags & BPF_F_USER_STACK; + struct perf_callchain_entry *trace; + bool kernel = !user; + int err = -EINVAL; + u64 *ips; + + if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | + BPF_F_USER_BUILD_ID))) + goto clear; + if (kernel && user_build_id) + goto clear; + + elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id) + : sizeof(u64); + if (unlikely(size % elem_size)) + goto clear; + + num_elem = size / elem_size; + if (sysctl_perf_event_max_stack < num_elem) + init_nr = 0; + else + init_nr = sysctl_perf_event_max_stack - num_elem; + trace = get_perf_callchain(regs, init_nr, kernel, user, + sysctl_perf_event_max_stack, false, false); + if (unlikely(!trace)) + goto err_fault; + + trace_nr = trace->nr - init_nr; + if (trace_nr < skip) + goto err_fault; + + trace_nr -= skip; + trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; + copy_len = trace_nr * elem_size; + ips = trace->ip + skip + init_nr; + if (user && user_build_id) + stack_map_get_build_id_offset(buf, ips, trace_nr, user); + else + memcpy(buf, ips, copy_len); + + if (size > copy_len) + memset(buf + copy_len, 0, size - copy_len); + return copy_len; + +err_fault: + err = -EFAULT; +clear: + memset(buf, 0, size); + return err; +} + +const struct bpf_func_proto bpf_get_stack_proto = { + .func = bpf_get_stack, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + /* Called from eBPF program */ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) { @@ -511,3 +608,16 @@ const struct bpf_map_ops stack_map_ops = { .map_update_elem = stack_map_update_elem, .map_delete_elem = stack_map_delete_elem, }; + +static int __init stack_map_init(void) +{ + int cpu; + struct stack_map_irq_work *work; + + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&up_read_work, cpu); + init_irq_work(&work->irq_work, do_up_read); + } + return 0; +} +subsys_initcall(stack_map_init); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 016ef9025827..b41c6cf2eb88 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -11,13 +11,17 @@ */ #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include <linux/bpf_lirc.h> +#include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/mmzone.h> #include <linux/anon_inodes.h> +#include <linux/fdtable.h> #include <linux/file.h> +#include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> #include <linux/version.h> @@ -26,6 +30,7 @@ #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> +#include <linux/btf.h> #include <linux/nospec.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ @@ -63,9 +68,9 @@ static const struct bpf_map_ops * const bpf_map_types[] = { * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ -static int check_uarg_tail_zero(void __user *uaddr, - size_t expected_size, - size_t actual_size) +int bpf_check_uarg_tail_zero(void __user *uaddr, + size_t expected_size, + size_t actual_size) { unsigned char __user *addr; unsigned char __user *end; @@ -273,6 +278,7 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) if (atomic_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map, do_idr_lock); + btf_put(map->btf); INIT_WORK(&map->work, bpf_map_free_deferred); schedule_work(&map->work); } @@ -282,6 +288,7 @@ void bpf_map_put(struct bpf_map *map) { __bpf_map_put(map, true); } +EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) { @@ -320,13 +327,15 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" - "memlock:\t%llu\n", + "memlock:\t%llu\n" + "map_id:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, - map->pages * 1ULL << PAGE_SHIFT); + map->pages * 1ULL << PAGE_SHIFT, + map->id); if (owner_prog_type) { seq_printf(m, "owner_prog_type:\t%u\n", @@ -418,7 +427,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD map_ifindex +#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -452,6 +461,33 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); + if (bpf_map_support_seq_show(map) && + (attr->btf_key_type_id || attr->btf_value_type_id)) { + struct btf *btf; + + if (!attr->btf_key_type_id || !attr->btf_value_type_id) { + err = -EINVAL; + goto free_map_nouncharge; + } + + btf = btf_get_by_fd(attr->btf_fd); + if (IS_ERR(btf)) { + err = PTR_ERR(btf); + goto free_map_nouncharge; + } + + err = map->ops->map_check_btf(map, btf, attr->btf_key_type_id, + attr->btf_value_type_id); + if (err) { + btf_put(btf); + goto free_map_nouncharge; + } + + map->btf = btf; + map->btf_key_type_id = attr->btf_key_type_id; + map->btf_value_type_id = attr->btf_value_type_id; + } + err = security_bpf_map_alloc(map); if (err) goto free_map_nouncharge; @@ -476,7 +512,6 @@ static int map_create(union bpf_attr *attr) return err; } - trace_bpf_map_create(map, err); return err; free_map: @@ -484,6 +519,7 @@ free_map: free_map_sec: security_bpf_map_free(map); free_map_nouncharge: + btf_put(map->btf); map->ops->map_free(map); return err; } @@ -516,6 +552,7 @@ struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref) atomic_inc(&map->usercnt); return map; } +EXPORT_SYMBOL_GPL(bpf_map_inc); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { @@ -538,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, { int refold; - refold = __atomic_add_unless(&map->refcnt, 1, 0); + refold = atomic_fetch_add_unless(&map->refcnt, 1, 0); if (refold >= BPF_MAX_REFCNT) { __bpf_map_put(map, false); @@ -635,7 +672,6 @@ static int map_lookup_elem(union bpf_attr *attr) if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; - trace_bpf_map_lookup_elem(map, ufd, key, value); err = 0; free_value: @@ -699,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_update_elem(map, key, value, attr->flags); goto out; - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP) { err = map->ops->map_update_elem(map, key, value, attr->flags); goto out; } @@ -732,8 +770,6 @@ static int map_update_elem(union bpf_attr *attr) __this_cpu_dec(bpf_prog_active); preempt_enable(); out: - if (!err) - trace_bpf_map_update_elem(map, ufd, key, value); free_value: kfree(value); free_key: @@ -786,8 +822,6 @@ static int map_delete_elem(union bpf_attr *attr) __this_cpu_dec(bpf_prog_active); preempt_enable(); out: - if (!err) - trace_bpf_map_delete_elem(map, ufd, key); kfree(key); err_put: fdput(f); @@ -851,7 +885,6 @@ out: if (copy_to_user(unext_key, next_key, map->key_size) != 0) goto free_next_key; - trace_bpf_map_next_key(map, ufd, key, next_key); err = 0; free_next_key: @@ -1003,15 +1036,9 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic_dec_and_test(&prog->aux->refcnt)) { - int i; - - trace_bpf_prog_put_rcu(prog); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); - - for (i = 0; i < prog->aux->func_cnt; i++) - bpf_prog_kallsyms_del(prog->aux->func[i]); - bpf_prog_kallsyms_del(prog); + bpf_prog_kallsyms_del_all(prog); call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } @@ -1042,11 +1069,13 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "prog_type:\t%u\n" "prog_jited:\t%u\n" "prog_tag:\t%s\n" - "memlock:\t%llu\n", + "memlock:\t%llu\n" + "prog_id:\t%u\n", prog->type, prog->jited, prog_tag, - prog->pages * 1ULL << PAGE_SHIFT); + prog->pages * 1ULL << PAGE_SHIFT, + prog->aux->id); } #endif @@ -1115,7 +1144,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; - refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0); + refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (refold >= BPF_MAX_REFCNT) { __bpf_prog_put(prog, false); @@ -1172,11 +1201,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { - struct bpf_prog *prog = __bpf_prog_get(ufd, &type, attach_drv); - - if (!IS_ERR(prog)) - trace_bpf_prog_get_type(prog); - return prog; + return __bpf_prog_get(ufd, &type, attach_drv); } EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); @@ -1226,6 +1251,8 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: return 0; default: return -EINVAL; @@ -1328,9 +1355,7 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_used_maps; - /* eBPF program is ready to be JITed */ - if (!prog->bpf_func) - prog = bpf_prog_select_runtime(prog, &err); + prog = bpf_prog_select_runtime(prog, &err); if (err < 0) goto free_used_maps; @@ -1351,10 +1376,10 @@ static int bpf_prog_load(union bpf_attr *attr) } bpf_prog_kallsyms_add(prog); - trace_bpf_prog_load(prog, err); return err; free_used_maps: + bpf_prog_kallsyms_del_subprogs(prog); free_used_maps(prog->aux); free_prog: bpf_prog_uncharge_memlock(prog); @@ -1460,8 +1485,6 @@ out_free_tp: return err; } -#ifdef CONFIG_CGROUP_BPF - static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { @@ -1476,40 +1499,6 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, #define BPF_PROG_ATTACH_LAST_FIELD attach_flags -static int sockmap_get_from_fd(const union bpf_attr *attr, - int type, bool attach) -{ - struct bpf_prog *prog = NULL; - int ufd = attr->target_fd; - struct bpf_map *map; - struct fd f; - int err; - - f = fdget(ufd); - map = __bpf_map_get(f); - if (IS_ERR(map)) - return PTR_ERR(map); - - if (attach) { - prog = bpf_prog_get_type(attr->attach_bpf_fd, type); - if (IS_ERR(prog)) { - fdput(f); - return PTR_ERR(prog); - } - } - - err = sock_map_prog(map, prog, attr->attach_type); - if (err) { - fdput(f); - if (prog) - bpf_prog_put(prog); - return err; - } - - fdput(f); - return 0; -} - #define BPF_F_ATTACH_MASK \ (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI) @@ -1517,7 +1506,6 @@ static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; struct bpf_prog *prog; - struct cgroup *cgrp; int ret; if (!capable(CAP_NET_ADMIN)) @@ -1543,6 +1531,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; break; case BPF_CGROUP_SOCK_OPS: @@ -1552,10 +1542,15 @@ static int bpf_prog_attach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true); + ptype = BPF_PROG_TYPE_SK_MSG; + break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true); + ptype = BPF_PROG_TYPE_SK_SKB; + break; + case BPF_LIRC_MODE2: + ptype = BPF_PROG_TYPE_LIRC_MODE2; + break; default: return -EINVAL; } @@ -1569,18 +1564,20 @@ static int bpf_prog_attach(const union bpf_attr *attr) return -EINVAL; } - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) { - bpf_prog_put(prog); - return PTR_ERR(cgrp); + switch (ptype) { + case BPF_PROG_TYPE_SK_SKB: + case BPF_PROG_TYPE_SK_MSG: + ret = sockmap_get_from_fd(attr, ptype, prog); + break; + case BPF_PROG_TYPE_LIRC_MODE2: + ret = lirc_prog_attach(attr, prog); + break; + default: + ret = cgroup_bpf_prog_attach(attr, ptype, prog); } - ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, - attr->attach_flags); if (ret) bpf_prog_put(prog); - cgroup_put(cgrp); - return ret; } @@ -1589,9 +1586,6 @@ static int bpf_prog_attach(const union bpf_attr *attr) static int bpf_prog_detach(const union bpf_attr *attr) { enum bpf_prog_type ptype; - struct bpf_prog *prog; - struct cgroup *cgrp; - int ret; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -1613,6 +1607,8 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; break; case BPF_CGROUP_SOCK_OPS: @@ -1622,27 +1618,17 @@ static int bpf_prog_detach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false); + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false); + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL); + case BPF_LIRC_MODE2: + return lirc_prog_detach(attr); default: return -EINVAL; } - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - - prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); - if (IS_ERR(prog)) - prog = NULL; - - ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); - if (prog) - bpf_prog_put(prog); - cgroup_put(cgrp); - return ret; + return cgroup_bpf_prog_detach(attr, ptype); } #define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt @@ -1650,9 +1636,6 @@ static int bpf_prog_detach(const union bpf_attr *attr) static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - struct cgroup *cgrp; - int ret; - if (!capable(CAP_NET_ADMIN)) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) @@ -1670,20 +1653,19 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: break; + case BPF_LIRC_MODE2: + return lirc_prog_query(attr, uattr); default: return -EINVAL; } - cgrp = cgroup_get_from_fd(attr->query.target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - ret = cgroup_bpf_query(cgrp, attr, uattr); - cgroup_put(cgrp); - return ret; + + return cgroup_bpf_prog_query(attr, uattr); } -#endif /* CONFIG_CGROUP_BPF */ #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration @@ -1879,7 +1861,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, u32 ulen; int err; - err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -1892,6 +1874,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.load_time = prog->aux->load_time; info.created_by_uid = from_kuid_munged(current_user_ns(), prog->aux->user->uid); + info.gpl_compatible = prog->gpl_compatible; memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); @@ -1912,6 +1895,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, if (!capable(CAP_SYS_ADMIN)) { info.jited_prog_len = 0; info.xlated_prog_len = 0; + info.nr_jited_ksyms = 0; goto done; } @@ -1948,18 +1932,93 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, * for offload. */ ulen = info.jited_prog_len; - info.jited_prog_len = prog->jited_len; + if (prog->aux->func_cnt) { + u32 i; + + info.jited_prog_len = 0; + for (i = 0; i < prog->aux->func_cnt; i++) + info.jited_prog_len += prog->aux->func[i]->jited_len; + } else { + info.jited_prog_len = prog->jited_len; + } + if (info.jited_prog_len && ulen) { if (bpf_dump_raw_ok()) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); - if (copy_to_user(uinsns, prog->bpf_func, ulen)) - return -EFAULT; + + /* for multi-function programs, copy the JITed + * instructions for all the functions + */ + if (prog->aux->func_cnt) { + u32 len, free, i; + u8 *img; + + free = ulen; + for (i = 0; i < prog->aux->func_cnt; i++) { + len = prog->aux->func[i]->jited_len; + len = min_t(u32, len, free); + img = (u8 *) prog->aux->func[i]->bpf_func; + if (copy_to_user(uinsns, img, len)) + return -EFAULT; + uinsns += len; + free -= len; + if (!free) + break; + } + } else { + if (copy_to_user(uinsns, prog->bpf_func, ulen)) + return -EFAULT; + } } else { info.jited_prog_insns = 0; } } + ulen = info.nr_jited_ksyms; + info.nr_jited_ksyms = prog->aux->func_cnt; + if (info.nr_jited_ksyms && ulen) { + if (bpf_dump_raw_ok()) { + u64 __user *user_ksyms; + ulong ksym_addr; + u32 i; + + /* copy the address of the kernel symbol + * corresponding to each function + */ + ulen = min_t(u32, info.nr_jited_ksyms, ulen); + user_ksyms = u64_to_user_ptr(info.jited_ksyms); + for (i = 0; i < ulen; i++) { + ksym_addr = (ulong) prog->aux->func[i]->bpf_func; + ksym_addr &= PAGE_MASK; + if (put_user((u64) ksym_addr, &user_ksyms[i])) + return -EFAULT; + } + } else { + info.jited_ksyms = 0; + } + } + + ulen = info.nr_jited_func_lens; + info.nr_jited_func_lens = prog->aux->func_cnt; + if (info.nr_jited_func_lens && ulen) { + if (bpf_dump_raw_ok()) { + u32 __user *user_lens; + u32 func_len, i; + + /* copy the JITed image lengths for each function */ + ulen = min_t(u32, info.nr_jited_func_lens, ulen); + user_lens = u64_to_user_ptr(info.jited_func_lens); + for (i = 0; i < ulen; i++) { + func_len = prog->aux->func[i]->jited_len; + if (put_user(func_len, &user_lens[i])) + return -EFAULT; + } + } else { + info.jited_func_lens = 0; + } + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) @@ -1977,7 +2036,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, u32 info_len = attr->info.info_len; int err; - err = check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -1990,6 +2049,12 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.map_flags = map->map_flags; memcpy(info.name, map->name, sizeof(map->name)); + if (map->btf) { + info.btf_id = btf_id(map->btf); + info.btf_key_type_id = map->btf_key_type_id; + info.btf_value_type_id = map->btf_value_type_id; + } + if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_info_fill(&info, map); if (err) @@ -2003,6 +2068,21 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, return 0; } +static int bpf_btf_get_info_by_fd(struct btf *btf, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info); + u32 info_len = attr->info.info_len; + int err; + + err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len); + if (err) + return err; + + return btf_get_info_by_fd(btf, attr, uattr); +} + #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, @@ -2025,6 +2105,8 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, else if (f.file->f_op == &bpf_map_fops) err = bpf_map_get_info_by_fd(f.file->private_data, attr, uattr); + else if (f.file->f_op == &btf_fops) + err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr); else err = -EINVAL; @@ -2032,6 +2114,158 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } +#define BPF_BTF_LOAD_LAST_FIELD btf_log_level + +static int bpf_btf_load(const union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_BTF_LOAD)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return btf_new_fd(attr); +} + +#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id + +static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return btf_get_fd_by_id(attr->btf_id); +} + +static int bpf_task_fd_query_copy(const union bpf_attr *attr, + union bpf_attr __user *uattr, + u32 prog_id, u32 fd_type, + const char *buf, u64 probe_offset, + u64 probe_addr) +{ + char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf); + u32 len = buf ? strlen(buf) : 0, input_len; + int err = 0; + + if (put_user(len, &uattr->task_fd_query.buf_len)) + return -EFAULT; + input_len = attr->task_fd_query.buf_len; + if (input_len && ubuf) { + if (!len) { + /* nothing to copy, just make ubuf NULL terminated */ + char zero = '\0'; + + if (put_user(zero, ubuf)) + return -EFAULT; + } else if (input_len >= len + 1) { + /* ubuf can hold the string with NULL terminator */ + if (copy_to_user(ubuf, buf, len + 1)) + return -EFAULT; + } else { + /* ubuf cannot hold the string with NULL terminator, + * do a partial copy with NULL terminator. + */ + char zero = '\0'; + + err = -ENOSPC; + if (copy_to_user(ubuf, buf, input_len - 1)) + return -EFAULT; + if (put_user(zero, ubuf + input_len - 1)) + return -EFAULT; + } + } + + if (put_user(prog_id, &uattr->task_fd_query.prog_id) || + put_user(fd_type, &uattr->task_fd_query.fd_type) || + put_user(probe_offset, &uattr->task_fd_query.probe_offset) || + put_user(probe_addr, &uattr->task_fd_query.probe_addr)) + return -EFAULT; + + return err; +} + +#define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr + +static int bpf_task_fd_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + pid_t pid = attr->task_fd_query.pid; + u32 fd = attr->task_fd_query.fd; + const struct perf_event *event; + struct files_struct *files; + struct task_struct *task; + struct file *file; + int err; + + if (CHECK_ATTR(BPF_TASK_FD_QUERY)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (attr->task_fd_query.flags != 0) + return -EINVAL; + + task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + if (!task) + return -ENOENT; + + files = get_files_struct(task); + put_task_struct(task); + if (!files) + return -ENOENT; + + err = 0; + spin_lock(&files->file_lock); + file = fcheck_files(files, fd); + if (!file) + err = -EBADF; + else + get_file(file); + spin_unlock(&files->file_lock); + put_files_struct(files); + + if (err) + goto out; + + if (file->f_op == &bpf_raw_tp_fops) { + struct bpf_raw_tracepoint *raw_tp = file->private_data; + struct bpf_raw_event_map *btp = raw_tp->btp; + + err = bpf_task_fd_query_copy(attr, uattr, + raw_tp->prog->aux->id, + BPF_FD_TYPE_RAW_TRACEPOINT, + btp->tp->name, 0, 0); + goto put_file; + } + + event = perf_get_event(file); + if (!IS_ERR(event)) { + u64 probe_offset, probe_addr; + u32 prog_id, fd_type; + const char *buf; + + err = bpf_get_perf_event_info(event, &prog_id, &fd_type, + &buf, &probe_offset, + &probe_addr); + if (!err) + err = bpf_task_fd_query_copy(attr, uattr, prog_id, + fd_type, buf, + probe_offset, + probe_addr); + goto put_file; + } + + err = -ENOTSUPP; +put_file: + fput(file); +out: + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -2040,7 +2274,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN)) return -EPERM; - err = check_uarg_tail_zero(uattr, sizeof(attr), size); + err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; size = min_t(u32, size, sizeof(attr)); @@ -2078,7 +2312,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; -#ifdef CONFIG_CGROUP_BPF case BPF_PROG_ATTACH: err = bpf_prog_attach(&attr); break; @@ -2088,7 +2321,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_QUERY: err = bpf_prog_query(&attr, uattr); break; -#endif case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr); break; @@ -2112,6 +2344,15 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; + case BPF_BTF_LOAD: + err = bpf_btf_load(&attr); + break; + case BPF_BTF_GET_FD_BY_ID: + err = bpf_btf_get_fd_by_id(&attr); + break; + case BPF_TASK_FD_QUERY: + err = bpf_task_fd_query(&attr, uattr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index 1f4bf68c12db..938d41211be7 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -43,6 +43,16 @@ struct tnum tnum_rshift(struct tnum a, u8 shift) return TNUM(a.value >> shift, a.mask >> shift); } +struct tnum tnum_arshift(struct tnum a, u8 min_shift) +{ + /* if a.value is negative, arithmetic shifting by minimum shift + * will have larger negative offset compared to more shifting. + * If a.value is nonnegative, arithmetic shifting by minimum shift + * will have larger positive offset compare to more shifting. + */ + return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); +} + struct tnum tnum_add(struct tnum a, struct tnum b) { u64 sm, sv, sigma, chi, mu; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1904e814f282..63aaac52a265 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -22,6 +22,7 @@ #include <linux/stringify.h> #include <linux/bsearch.h> #include <linux/sort.h> +#include <linux/perf_event.h> #include "disasm.h" @@ -186,6 +187,8 @@ struct bpf_call_arg_meta { bool pkt_access; int regno; int access_size; + s64 msize_smax_value; + u64 msize_umax_value; }; static DEFINE_MUTEX(bpf_verifier_lock); @@ -760,18 +763,19 @@ enum reg_arg_type { static int cmp_subprogs(const void *a, const void *b) { - return *(int *)a - *(int *)b; + return ((struct bpf_subprog_info *)a)->start - + ((struct bpf_subprog_info *)b)->start; } static int find_subprog(struct bpf_verifier_env *env, int off) { - u32 *p; + struct bpf_subprog_info *p; - p = bsearch(&off, env->subprog_starts, env->subprog_cnt, - sizeof(env->subprog_starts[0]), cmp_subprogs); + p = bsearch(&off, env->subprog_info, env->subprog_cnt, + sizeof(env->subprog_info[0]), cmp_subprogs); if (!p) return -ENOENT; - return p - env->subprog_starts; + return p - env->subprog_info; } @@ -791,18 +795,24 @@ static int add_subprog(struct bpf_verifier_env *env, int off) verbose(env, "too many subprograms\n"); return -E2BIG; } - env->subprog_starts[env->subprog_cnt++] = off; - sort(env->subprog_starts, env->subprog_cnt, - sizeof(env->subprog_starts[0]), cmp_subprogs, NULL); + env->subprog_info[env->subprog_cnt++].start = off; + sort(env->subprog_info, env->subprog_cnt, + sizeof(env->subprog_info[0]), cmp_subprogs, NULL); return 0; } static int check_subprogs(struct bpf_verifier_env *env) { int i, ret, subprog_start, subprog_end, off, cur_subprog = 0; + struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; + /* Add entry function. */ + ret = add_subprog(env, 0); + if (ret < 0) + return ret; + /* determine subprog starts. The end is one before the next starts */ for (i = 0; i < insn_cnt; i++) { if (insn[i].code != (BPF_JMP | BPF_CALL)) @@ -822,16 +832,18 @@ static int check_subprogs(struct bpf_verifier_env *env) return ret; } + /* Add a fake 'exit' subprog which could simplify subprog iteration + * logic. 'subprog_cnt' should not be increased. + */ + subprog[env->subprog_cnt].start = insn_cnt; + if (env->log.level > 1) for (i = 0; i < env->subprog_cnt; i++) - verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]); + verbose(env, "func#%d @%d\n", i, subprog[i].start); /* now check that all jumps are within the same subprog */ - subprog_start = 0; - if (env->subprog_cnt == cur_subprog) - subprog_end = insn_cnt; - else - subprog_end = env->subprog_starts[cur_subprog++]; + subprog_start = subprog[cur_subprog].start; + subprog_end = subprog[cur_subprog + 1].start; for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; @@ -856,10 +868,9 @@ next: return -EINVAL; } subprog_start = subprog_end; - if (env->subprog_cnt == cur_subprog) - subprog_end = insn_cnt; - else - subprog_end = env->subprog_starts[cur_subprog++]; + cur_subprog++; + if (cur_subprog < env->subprog_cnt) + subprog_end = subprog[cur_subprog + 1].start; } } return 0; @@ -1298,6 +1309,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, switch (env->prog->type) { case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: /* dst_input() and dst_output() can't write for now */ if (t == BPF_WRITE) return false; @@ -1517,13 +1529,13 @@ static int update_stack_depth(struct bpf_verifier_env *env, const struct bpf_func_state *func, int off) { - u16 stack = env->subprog_stack_depth[func->subprogno]; + u16 stack = env->subprog_info[func->subprogno].stack_depth; if (stack >= -off) return 0; /* update known max for given subprogram */ - env->subprog_stack_depth[func->subprogno] = -off; + env->subprog_info[func->subprogno].stack_depth = -off; return 0; } @@ -1535,9 +1547,9 @@ static int update_stack_depth(struct bpf_verifier_env *env, */ static int check_max_stack_depth(struct bpf_verifier_env *env) { - int depth = 0, frame = 0, subprog = 0, i = 0, subprog_end; + int depth = 0, frame = 0, idx = 0, i = 0, subprog_end; + struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; - int insn_cnt = env->prog->len; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; @@ -1545,17 +1557,14 @@ process_func: /* round up to 32-bytes, since this is granularity * of interpreter stack size */ - depth += round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32); + depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); if (depth > MAX_BPF_STACK) { verbose(env, "combined stack size of %d calls is %d. Too large\n", frame + 1, depth); return -EACCES; } continue_func: - if (env->subprog_cnt == subprog) - subprog_end = insn_cnt; - else - subprog_end = env->subprog_starts[subprog]; + subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { if (insn[i].code != (BPF_JMP | BPF_CALL)) continue; @@ -1563,17 +1572,16 @@ continue_func: continue; /* remember insn and function to return to */ ret_insn[frame] = i + 1; - ret_prog[frame] = subprog; + ret_prog[frame] = idx; /* find the callee */ i = i + insn[i].imm + 1; - subprog = find_subprog(env, i); - if (subprog < 0) { + idx = find_subprog(env, i); + if (idx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", i); return -EFAULT; } - subprog++; frame++; if (frame >= MAX_CALL_FRAMES) { WARN_ONCE(1, "verifier bug. Call stack is too deep\n"); @@ -1586,10 +1594,10 @@ continue_func: */ if (frame == 0) return 0; - depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32); + depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); frame--; i = ret_insn[frame]; - subprog = ret_prog[frame]; + idx = ret_prog[frame]; goto continue_func; } @@ -1605,11 +1613,34 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, start); return -EFAULT; } - subprog++; - return env->subprog_stack_depth[subprog]; + return env->subprog_info[subprog].stack_depth; } #endif +static int check_ctx_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) +{ + /* Access to ctx or passing it to a helper is only allowed in + * its original, unmodified form. + */ + + if (reg->off) { + verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n", + regno, reg->off); + return -EACCES; + } + + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf); + return -EACCES; + } + + return 0; +} + /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE */ @@ -1679,24 +1710,11 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn verbose(env, "R%d leaks addr into ctx\n", value_regno); return -EACCES; } - /* ctx accesses must be at a fixed offset, so that we can - * determine what type of data were returned. - */ - if (reg->off) { - verbose(env, - "dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n", - regno, reg->off, off - reg->off); - return -EACCES; - } - if (!tnum_is_const(reg->var_off) || reg->var_off.value) { - char tn_buf[48]; - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, - "variable ctx access var_off=%s off=%d size=%d", - tn_buf, off, size); - return -EACCES; - } + err = check_ctx_reg(env, reg, regno); + if (err < 0) + return err; + err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a @@ -1961,7 +1979,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - if (!type_is_pkt_pointer(type) && + if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || @@ -1977,6 +1995,9 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, expected_type = PTR_TO_CTX; if (type != expected_type) goto err_type; + err = check_ctx_reg(env, reg, regno); + if (err < 0) + return err; } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be @@ -2013,14 +2034,9 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } - if (type_is_pkt_pointer(type)) - err = check_packet_access(env, regno, reg->off, - meta->map_ptr->key_size, - false); - else - err = check_stack_boundary(env, regno, - meta->map_ptr->key_size, - false, NULL); + err = check_helper_mem_access(env, regno, + meta->map_ptr->key_size, false, + NULL); } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity @@ -2030,17 +2046,18 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } - if (type_is_pkt_pointer(type)) - err = check_packet_access(env, regno, reg->off, - meta->map_ptr->value_size, - false); - else - err = check_stack_boundary(env, regno, - meta->map_ptr->value_size, - false, NULL); + err = check_helper_mem_access(env, regno, + meta->map_ptr->value_size, false, + NULL); } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); + /* remember the mem_size which may be used later + * to refine return values. + */ + meta->msize_smax_value = reg->smax_value; + meta->msize_umax_value = reg->umax_value; + /* The register is SCALAR_VALUE; the access check * happens using its boundaries. */ @@ -2118,8 +2135,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_redirect_map) goto error; break; - /* Restrict bpf side of cpumap, open when use-cases appear */ + /* Restrict bpf side of cpumap and xskmap, open when use-cases + * appear. + */ case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: if (func_id != BPF_FUNC_redirect_map) goto error; break; @@ -2135,6 +2155,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_msg_redirect_map) goto error; break; + case BPF_MAP_TYPE_SOCKHASH: + if (func_id != BPF_FUNC_sk_redirect_hash && + func_id != BPF_FUNC_sock_hash_update && + func_id != BPF_FUNC_map_delete_elem && + func_id != BPF_FUNC_msg_redirect_hash) + goto error; + break; default: break; } @@ -2144,7 +2171,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_tail_call: if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; - if (env->subprog_cnt) { + if (env->subprog_cnt > 1) { verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n"); return -EINVAL; } @@ -2166,16 +2193,20 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && - map->map_type != BPF_MAP_TYPE_CPUMAP) + map->map_type != BPF_MAP_TYPE_CPUMAP && + map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; break; case BPF_FUNC_sk_redirect_map: case BPF_FUNC_msg_redirect_map: + case BPF_FUNC_sock_map_update: if (map->map_type != BPF_MAP_TYPE_SOCKMAP) goto error; break; - case BPF_FUNC_sock_map_update: - if (map->map_type != BPF_MAP_TYPE_SOCKMAP) + case BPF_FUNC_sk_redirect_hash: + case BPF_FUNC_msg_redirect_hash: + case BPF_FUNC_sock_hash_update: + if (map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; default: @@ -2316,7 +2347,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* remember the callsite, it will be used by bpf_exit */ *insn_idx /* callsite */, state->curframe + 1 /* frameno within this callchain */, - subprog + 1 /* subprog number within this prog */); + subprog /* subprog number within this prog */); /* copy r1 - r5 args that callee can access */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) @@ -2380,6 +2411,23 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return 0; } +static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, + int func_id, + struct bpf_call_arg_meta *meta) +{ + struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; + + if (ret_type != RET_INTEGER || + (func_id != BPF_FUNC_get_stack && + func_id != BPF_FUNC_probe_read_str)) + return; + + ret_reg->smax_value = meta->msize_smax_value; + ret_reg->umax_value = meta->msize_umax_value; + __reg_deduce_bounds(ret_reg); + __reg_bound_offset(ret_reg); +} + static int record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) @@ -2387,8 +2435,11 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; if (func_id != BPF_FUNC_tail_call && - func_id != BPF_FUNC_map_lookup_elem) + func_id != BPF_FUNC_map_lookup_elem && + func_id != BPF_FUNC_map_update_elem && + func_id != BPF_FUNC_map_delete_elem) return 0; + if (meta->map_ptr == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; @@ -2428,7 +2479,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { - verbose(env, "cannot call GPL only function from proprietary program\n"); + verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n"); return -EINVAL; } @@ -2516,10 +2567,30 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } + do_refine_retval_range(regs, fn->ret_type, func_id, &meta); + err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) return err; + if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) { + const char *err_str; + +#ifdef CONFIG_PERF_EVENTS + err = get_callchain_buffers(sysctl_perf_event_max_stack); + err_str = "cannot get callchain buffer for func %s#%d\n"; +#else + err = -ENOTSUPP; + err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n"; +#endif + if (err) { + verbose(env, err_str, func_id_name(func_id), func_id); + return err; + } + + env->prog->has_callchain_buf = true; + } + if (changes_data) clear_all_pkt_pointers(env); return 0; @@ -2964,10 +3035,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, dst_reg->umin_value <<= umin_val; dst_reg->umax_value <<= umax_val; } - if (src_known) - dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); - else - dst_reg->var_off = tnum_lshift(tnum_unknown, umin_val); + dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); break; @@ -2995,16 +3063,35 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; - if (src_known) - dst_reg->var_off = tnum_rshift(dst_reg->var_off, - umin_val); - else - dst_reg->var_off = tnum_rshift(tnum_unknown, umin_val); + dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); dst_reg->umin_value >>= umax_val; dst_reg->umax_value >>= umin_val; /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); break; + case BPF_ARSH: + if (umax_val >= insn_bitness) { + /* Shifts greater than 31 or 63 are undefined. + * This includes shifts by a negative number. + */ + mark_reg_unknown(env, regs, insn->dst_reg); + break; + } + + /* Upon reaching here, src_known is true and + * umax_val is equal to umin_val. + */ + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); + + /* blow away the dst_reg umin_value/umax_value and rely on + * dst_reg var_off to refine the result. + */ + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + __update_reg_bounds(dst_reg); + break; default: mark_reg_unknown(env, regs, insn->dst_reg); break; @@ -3888,7 +3975,12 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (env->subprog_cnt) { + if (!env->ops->gen_ld_abs) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } + + if (env->subprog_cnt > 1) { /* when program has LD_ABS insn JITs and interpreter assume * that r1 == ctx == skb which is not the case for callees * that can have arbitrary arguments. It's problematic @@ -4919,15 +5011,15 @@ process_bpf_exit: verbose(env, "processed %d insns (limit %d), stack depth ", insn_processed, BPF_COMPLEXITY_LIMIT_INSNS); - for (i = 0; i < env->subprog_cnt + 1; i++) { - u32 depth = env->subprog_stack_depth[i]; + for (i = 0; i < env->subprog_cnt; i++) { + u32 depth = env->subprog_info[i].stack_depth; verbose(env, "%d", depth); - if (i + 1 < env->subprog_cnt + 1) + if (i + 1 < env->subprog_cnt) verbose(env, "+"); } verbose(env, "\n"); - env->prog->aux->stack_depth = env->subprog_stack_depth[0]; + env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } @@ -5051,7 +5143,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded - * and all maps are released in free_bpf_prog_info() + * and all maps are released in free_used_maps() */ map = bpf_map_inc(map, false); if (IS_ERR(map)) { @@ -5114,7 +5206,8 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, if (cnt == 1) return 0; - new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len); + new_data = vzalloc(array_size(prog_len, + sizeof(struct bpf_insn_aux_data))); if (!new_data) return -ENOMEM; memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); @@ -5133,10 +5226,11 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len if (len == 1) return; - for (i = 0; i < env->subprog_cnt; i++) { - if (env->subprog_starts[i] < off) + /* NOTE: fake 'exit' subprog should be updated as well. */ + for (i = 0; i <= env->subprog_cnt; i++) { + if (env->subprog_info[i].start < off) continue; - env->subprog_starts[i] += len - 1; + env->subprog_info[i].start += len - 1; } } @@ -5210,7 +5304,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } } - if (!ops->convert_ctx_access) + if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; @@ -5270,6 +5364,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) */ is_narrower_load = size < ctx_field_size; if (is_narrower_load) { + u32 size_default = bpf_ctx_off_adjust_machine(ctx_field_size); u32 off = insn->off; u8 size_code; @@ -5284,7 +5379,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) else if (ctx_field_size == 8) size_code = BPF_DW; - insn->off = off & ~(ctx_field_size - 1); + insn->off = off & ~(size_default - 1); insn->code = BPF_LDX | BPF_MEM | size_code; } @@ -5328,13 +5423,17 @@ static int jit_subprogs(struct bpf_verifier_env *env) void *old_bpf_func; int err = -ENOMEM; - if (env->subprog_cnt == 0) + if (env->subprog_cnt <= 1) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; + /* Upon error here we cannot fall back to interpreter but + * need a hard reject of the program. Thus -EFAULT is + * propagated in any case. + */ subprog = find_subprog(env, i + insn->imm + 1); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", @@ -5344,7 +5443,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) /* temporarily remember subprog id inside insn instead of * aux_data, since next loop will split up all insns into funcs */ - insn->off = subprog + 1; + insn->off = subprog; /* remember original imm in case JIT fails and fallback * to interpreter will be needed */ @@ -5353,16 +5452,13 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn->imm = 1; } - func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL); + func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) - return -ENOMEM; + goto out_undo_insn; - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; - if (env->subprog_cnt == i) - subprog_end = prog->len; - else - subprog_end = env->subprog_starts[i]; + subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER); @@ -5379,7 +5475,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) * Long term would need debug info to populate names */ func[i]->aux->name[0] = 'F'; - func[i]->aux->stack_depth = env->subprog_stack_depth[i]; + func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { @@ -5392,25 +5488,38 @@ static int jit_subprogs(struct bpf_verifier_env *env) * now populate all bpf_calls with correct addresses and * run last pass of JIT */ - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; subprog = insn->off; - insn->off = 0; insn->imm = (u64 (*)(u64, u64, u64, u64, u64)) func[subprog]->bpf_func - __bpf_call_base; } + + /* we use the aux data to keep a list of the start addresses + * of the JITed images for each function in the program + * + * for some architectures, such as powerpc64, the imm field + * might not be large enough to hold the offset of the start + * address of the callee's JITed image from __bpf_call_base + * + * in such cases, we can lookup the start address of a callee + * by using its subprog id, available from the off field of + * the call instruction, as an index for this list + */ + func[i]->aux->func = func; + func[i]->aux->func_cnt = env->subprog_cnt; } - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); - err = -EFAULT; + err = -ENOTSUPP; goto out_free; } cond_resched(); @@ -5419,7 +5528,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) /* finally lock prog and jit images for all functions and * populate kallsysm */ - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { bpf_prog_lock_ro(func[i]); bpf_prog_kallsyms_add(func[i]); } @@ -5429,29 +5538,25 @@ static int jit_subprogs(struct bpf_verifier_env *env) * later look the same as if they were interpreted only. */ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { - unsigned long addr; - if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; insn->off = env->insn_aux_data[i].call_imm; subprog = find_subprog(env, i + insn->off + 1); - addr = (unsigned long)func[subprog + 1]->bpf_func; - addr &= PAGE_MASK; - insn->imm = (u64 (*)(u64, u64, u64, u64, u64)) - addr - __bpf_call_base; + insn->imm = subprog; } prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->aux->func = func; - prog->aux->func_cnt = env->subprog_cnt + 1; + prog->aux->func_cnt = env->subprog_cnt; return 0; out_free: - for (i = 0; i <= env->subprog_cnt; i++) + for (i = 0; i < env->subprog_cnt; i++) if (func[i]) bpf_jit_free(func[i]); kfree(func); +out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { @@ -5478,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env) err = jit_subprogs(env); if (err == 0) return 0; + if (err == -EFAULT) + return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON for (i = 0; i < prog->len; i++, insn++) { @@ -5505,6 +5612,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; + const struct bpf_map_ops *ops; struct bpf_insn_aux_data *aux; struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; @@ -5552,6 +5660,25 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) continue; } + if (BPF_CLASS(insn->code) == BPF_LD && + (BPF_MODE(insn->code) == BPF_ABS || + BPF_MODE(insn->code) == BPF_IND)) { + cnt = env->ops->gen_ld_abs(insn, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (insn->code != (BPF_JMP | BPF_CALL)) continue; if (insn->src_reg == BPF_PSEUDO_CALL) @@ -5615,35 +5742,61 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) } /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup - * handlers are currently limited to 64 bit only. + * and other inlining handlers are currently limited to 64 bit + * only. */ if (prog->jit_requested && BITS_PER_LONG == 64 && - insn->imm == BPF_FUNC_map_lookup_elem) { + (insn->imm == BPF_FUNC_map_lookup_elem || + insn->imm == BPF_FUNC_map_update_elem || + insn->imm == BPF_FUNC_map_delete_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; map_ptr = BPF_MAP_PTR(aux->map_state); - if (!map_ptr->ops->map_gen_lookup) - goto patch_call_imm; + ops = map_ptr->ops; + if (insn->imm == BPF_FUNC_map_lookup_elem && + ops->map_gen_lookup) { + cnt = ops->map_gen_lookup(map_ptr, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } - cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf); - if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; - } + new_prog = bpf_patch_insn_data(env, i + delta, + insn_buf, cnt); + if (!new_prog) + return -ENOMEM; - new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, - cnt); - if (!new_prog) - return -ENOMEM; + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } - delta += cnt - 1; + BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_delete_elem, + (int (*)(struct bpf_map *map, void *key))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_update_elem, + (int (*)(struct bpf_map *map, void *key, void *value, + u64 flags))NULL)); + switch (insn->imm) { + case BPF_FUNC_map_lookup_elem: + insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - + __bpf_call_base; + continue; + case BPF_FUNC_map_update_elem: + insn->imm = BPF_CAST_CALL(ops->map_update_elem) - + __bpf_call_base; + continue; + case BPF_FUNC_map_delete_elem: + insn->imm = BPF_CAST_CALL(ops->map_delete_elem) - + __bpf_call_base; + continue; + } - /* keep walking new program and skip insns we just inserted */ - env->prog = prog = new_prog; - insn = new_prog->insnsi + i + delta; - continue; + goto patch_call_imm; } if (insn->imm == BPF_FUNC_redirect_map) { @@ -5725,8 +5878,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) return -ENOMEM; log = &env->log; - env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) * - (*prog)->len); + env->insn_aux_data = + vzalloc(array_size(sizeof(struct bpf_insn_aux_data), + (*prog)->len)); ret = -ENOMEM; if (!env->insn_aux_data) goto err_free_env; @@ -5755,16 +5909,16 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; + ret = replace_map_fd_with_map_ptr(env); + if (ret < 0) + goto skip_full_check; + if (bpf_prog_is_dev_bound(env->prog->aux)) { ret = bpf_prog_offload_verifier_prep(env); if (ret) - goto err_unlock; + goto skip_full_check; } - ret = replace_map_fd_with_map_ptr(env); - if (ret < 0) - goto skip_full_check; - env->explored_states = kcalloc(env->prog->len, sizeof(struct bpf_verifier_state_list *), GFP_USER); @@ -5835,7 +5989,7 @@ skip_full_check: err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release - * them now. Otherwise free_bpf_prog_info() will release them. + * them now. Otherwise free_used_maps() will release them. */ release_maps(env); *prog = env->prog; diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c new file mode 100644 index 000000000000..b3c557476a8d --- /dev/null +++ b/kernel/bpf/xskmap.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XSKMAP used for AF_XDP sockets + * Copyright(c) 2018 Intel Corporation. + */ + +#include <linux/bpf.h> +#include <linux/capability.h> +#include <net/xdp_sock.h> +#include <linux/slab.h> +#include <linux/sched.h> + +struct xsk_map { + struct bpf_map map; + struct xdp_sock **xsk_map; + struct list_head __percpu *flush_list; +}; + +static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) +{ + int cpu, err = -EINVAL; + struct xsk_map *m; + u64 cost; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || + attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)) + return ERR_PTR(-EINVAL); + + m = kzalloc(sizeof(*m), GFP_USER); + if (!m) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&m->map, attr); + + cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *); + cost += sizeof(struct list_head) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_m; + + m->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* Notice returns -EPERM on if map size is larger than memlock limit */ + err = bpf_map_precharge_memlock(m->map.pages); + if (err) + goto free_m; + + err = -ENOMEM; + + m->flush_list = alloc_percpu(struct list_head); + if (!m->flush_list) + goto free_m; + + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu)); + + m->xsk_map = bpf_map_area_alloc(m->map.max_entries * + sizeof(struct xdp_sock *), + m->map.numa_node); + if (!m->xsk_map) + goto free_percpu; + return &m->map; + +free_percpu: + free_percpu(m->flush_list); +free_m: + kfree(m); + return ERR_PTR(err); +} + +static void xsk_map_free(struct bpf_map *map) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + int i; + + synchronize_net(); + + for (i = 0; i < map->max_entries; i++) { + struct xdp_sock *xs; + + xs = m->xsk_map[i]; + if (!xs) + continue; + + sock_put((struct sock *)xs); + } + + free_percpu(m->flush_list); + bpf_map_area_free(m->xsk_map); + kfree(m); +} + +static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= m->map.max_entries) { + *next = 0; + return 0; + } + + if (index == m->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *xs; + + if (key >= map->max_entries) + return NULL; + + xs = READ_ONCE(m->xsk_map[key]); + return xs; +} + +int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct list_head *flush_list = this_cpu_ptr(m->flush_list); + int err; + + err = xsk_rcv(xs, xdp); + if (err) + return err; + + if (!xs->flush_node.prev) + list_add(&xs->flush_node, flush_list); + + return 0; +} + +void __xsk_map_flush(struct bpf_map *map) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct list_head *flush_list = this_cpu_ptr(m->flush_list); + struct xdp_sock *xs, *tmp; + + list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { + xsk_flush(xs); + __list_del(xs->flush_node.prev, xs->flush_node.next); + xs->flush_node.prev = NULL; + } +} + +static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) +{ + return NULL; +} + +static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + u32 i = *(u32 *)key, fd = *(u32 *)value; + struct xdp_sock *xs, *old_xs; + struct socket *sock; + int err; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(i >= m->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + + sock = sockfd_lookup(fd, &err); + if (!sock) + return err; + + if (sock->sk->sk_family != PF_XDP) { + sockfd_put(sock); + return -EOPNOTSUPP; + } + + xs = (struct xdp_sock *)sock->sk; + + if (!xsk_is_setup_for_bpf_map(xs)) { + sockfd_put(sock); + return -EOPNOTSUPP; + } + + sock_hold(sock->sk); + + old_xs = xchg(&m->xsk_map[i], xs); + if (old_xs) { + /* Make sure we've flushed everything. */ + synchronize_net(); + sock_put((struct sock *)old_xs); + } + + sockfd_put(sock); + return 0; +} + +static int xsk_map_delete_elem(struct bpf_map *map, void *key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *old_xs; + int k = *(u32 *)key; + + if (k >= map->max_entries) + return -EINVAL; + + old_xs = xchg(&m->xsk_map[k], NULL); + if (old_xs) { + /* Make sure we've flushed everything. */ + synchronize_net(); + sock_put((struct sock *)old_xs); + } + + return 0; +} + +const struct bpf_map_ops xsk_map_ops = { + .map_alloc = xsk_map_alloc, + .map_free = xsk_map_free, + .map_get_next_key = xsk_map_get_next_key, + .map_lookup_elem = xsk_map_lookup_elem, + .map_update_elem = xsk_map_update_elem, + .map_delete_elem = xsk_map_delete_elem, +}; + + diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index e06c97f3ed1a..8b4f0768efd6 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -195,9 +195,9 @@ struct cgroup_pidlist { static void *pidlist_allocate(int count) { if (PIDLIST_TOO_LARGE(count)) - return vmalloc(count * sizeof(pid_t)); + return vmalloc(array_size(count, sizeof(pid_t))); else - return kmalloc(count * sizeof(pid_t), GFP_KERNEL); + return kmalloc_array(count, sizeof(pid_t), GFP_KERNEL); } static void pidlist_free(void *p) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index acb66713f9b6..077370bf8964 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4820,8 +4820,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent) int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ - cgrp = kzalloc(sizeof(*cgrp) + - sizeof(cgrp->ancestor_ids[0]) * (level + 1), GFP_KERNEL); + cgrp = kzalloc(struct_size(cgrp, ancestor_ids, (level + 1)), + GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index b42037e6e81d..266f10cb7222 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -605,7 +605,7 @@ static inline int nr_cpusets(void) * load balancing domains (sched domains) as specified by that partial * partition. * - * See "What is sched_load_balance" in Documentation/cgroups/cpusets.txt + * See "What is sched_load_balance" in Documentation/cgroup-v1/cpusets.txt * for a background explanation of this. * * Does not return errors, on the theory that the callers of this @@ -683,7 +683,7 @@ static int generate_sched_domains(cpumask_var_t **domains, goto done; } - csa = kmalloc(nr_cpusets() * sizeof(cp), GFP_KERNEL); + csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; @@ -753,7 +753,8 @@ restart: * The rest of the code, including the scheduler, can deal with * dattr==NULL case. No need to abort if alloc fails. */ - dattr = kmalloc(ndoms * sizeof(struct sched_domain_attr), GFP_KERNEL); + dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr), + GFP_KERNEL); for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; diff --git a/kernel/compat.c b/kernel/compat.c index 702aa846ddac..8e40efc2928a 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -324,35 +324,6 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, return ret; } -/* Todo: Delete these extern declarations when get/put_compat_itimerspec64() - * are moved to kernel/time/time.c . - */ -extern int __compat_get_timespec64(struct timespec64 *ts64, - const struct compat_timespec __user *cts); -extern int __compat_put_timespec64(const struct timespec64 *ts64, - struct compat_timespec __user *cts); - -int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits) -{ - - if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || - __compat_get_timespec64(&its->it_value, &uits->it_value)) - return -EFAULT; - return 0; -} -EXPORT_SYMBOL_GPL(get_compat_itimerspec64); - -int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits) -{ - if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || - __compat_put_timespec64(&its->it_value, &uits->it_value)) - return -EFAULT; - return 0; -} -EXPORT_SYMBOL_GPL(put_compat_itimerspec64); - /* * We currently only need the following fields from the sigevent * structure: sigev_value, sigev_signo, sig_notify and (sometimes diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config index 946fb92418f7..81e9af7dcec2 100644 --- a/kernel/configs/android-recommended.config +++ b/kernel/configs/android-recommended.config @@ -12,7 +12,7 @@ CONFIG_BLK_DEV_DM=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_CC_STACKPROTECTOR_STRONG=y +CONFIG_STACKPROTECTOR_STRONG=y CONFIG_COMPACTION=y CONFIG_CPU_SW_DOMAIN_PAN=y CONFIG_DM_CRYPT=y diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config index 9bfdffc100da..7fa0c4ae6394 100644 --- a/kernel/configs/tiny.config +++ b/kernel/configs/tiny.config @@ -10,7 +10,3 @@ CONFIG_OPTIMIZE_INLINING=y # CONFIG_SLAB is not set # CONFIG_SLUB is not set CONFIG_SLOB=y -CONFIG_CC_STACKPROTECTOR_NONE=y -# CONFIG_CC_STACKPROTECTOR_REGULAR is not set -# CONFIG_CC_STACKPROTECTOR_STRONG is not set -# CONFIG_CC_STACKPROTECTOR_AUTO is not set diff --git a/kernel/cpu.c b/kernel/cpu.c index 0db8938fbb23..ed44d7d34c2d 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -60,6 +60,7 @@ struct cpuhp_cpu_state { bool rollback; bool single; bool bringup; + bool booted_once; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; @@ -290,6 +291,12 @@ void cpus_read_lock(void) } EXPORT_SYMBOL_GPL(cpus_read_lock); +int cpus_read_trylock(void) +{ + return percpu_down_read_trylock(&cpu_hotplug_lock); +} +EXPORT_SYMBOL_GPL(cpus_read_trylock); + void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); @@ -342,6 +349,85 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */ +#ifdef CONFIG_HOTPLUG_SMT +enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; +EXPORT_SYMBOL_GPL(cpu_smt_control); + +static bool cpu_smt_available __read_mostly; + +void __init cpu_smt_disable(bool force) +{ + if (cpu_smt_control == CPU_SMT_FORCE_DISABLED || + cpu_smt_control == CPU_SMT_NOT_SUPPORTED) + return; + + if (force) { + pr_info("SMT: Force disabled\n"); + cpu_smt_control = CPU_SMT_FORCE_DISABLED; + } else { + cpu_smt_control = CPU_SMT_DISABLED; + } +} + +/* + * The decision whether SMT is supported can only be done after the full + * CPU identification. Called from architecture code before non boot CPUs + * are brought up. + */ +void __init cpu_smt_check_topology_early(void) +{ + if (!topology_smt_supported()) + cpu_smt_control = CPU_SMT_NOT_SUPPORTED; +} + +/* + * If SMT was disabled by BIOS, detect it here, after the CPUs have been + * brought online. This ensures the smt/l1tf sysfs entries are consistent + * with reality. cpu_smt_available is set to true during the bringup of non + * boot CPUs when a SMT sibling is detected. Note, this may overwrite + * cpu_smt_control's previous setting. + */ +void __init cpu_smt_check_topology(void) +{ + if (!cpu_smt_available) + cpu_smt_control = CPU_SMT_NOT_SUPPORTED; +} + +static int __init smt_cmdline_disable(char *str) +{ + cpu_smt_disable(str && !strcmp(str, "force")); + return 0; +} +early_param("nosmt", smt_cmdline_disable); + +static inline bool cpu_smt_allowed(unsigned int cpu) +{ + if (topology_is_primary_thread(cpu)) + return true; + + /* + * If the CPU is not a 'primary' thread and the booted_once bit is + * set then the processor has SMT support. Store this information + * for the late check of SMT support in cpu_smt_check_topology(). + */ + if (per_cpu(cpuhp_state, cpu).booted_once) + cpu_smt_available = true; + + if (cpu_smt_control == CPU_SMT_ENABLED) + return true; + + /* + * On x86 it's required to boot all logical CPUs at least once so + * that the init code can get a chance to set CR4.MCE on each + * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any + * core will shutdown the machine. + */ + return !per_cpu(cpuhp_state, cpu).booted_once; +} +#else +static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } +#endif + static inline enum cpuhp_state cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) { @@ -422,6 +508,16 @@ static int bringup_wait_for_ap(unsigned int cpu) stop_machine_unpark(cpu); kthread_unpark(st->thread); + /* + * SMT soft disabling on X86 requires to bring the CPU out of the + * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The + * CPU marked itself as booted_once in cpu_notify_starting() so the + * cpu_smt_allowed() check will now return false if this is not the + * primary sibling. + */ + if (!cpu_smt_allowed(cpu)) + return -ECANCELED; + if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; @@ -754,7 +850,6 @@ static int takedown_cpu(unsigned int cpu) /* Park the smpboot threads */ kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread); - smpboot_park_threads(cpu); /* * Prevent irq alloc/free while the dying cpu reorganizes the @@ -907,20 +1002,19 @@ out: return ret; } +static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) +{ + if (cpu_hotplug_disabled) + return -EBUSY; + return _cpu_down(cpu, 0, target); +} + static int do_cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; cpu_maps_update_begin(); - - if (cpu_hotplug_disabled) { - err = -EBUSY; - goto out; - } - - err = _cpu_down(cpu, 0, target); - -out: + err = cpu_down_maps_locked(cpu, target); cpu_maps_update_done(); return err; } @@ -949,6 +1043,7 @@ void notify_cpu_starting(unsigned int cpu) int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ + st->booted_once = true; while (st->state < target) { st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); @@ -1058,6 +1153,10 @@ static int do_cpu_up(unsigned int cpu, enum cpuhp_state target) err = -EBUSY; goto out; } + if (!cpu_smt_allowed(cpu)) { + err = -EPERM; + goto out; + } err = _cpu_up(cpu, 0, target); out: @@ -1274,7 +1373,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { - .name = "timers:dead", + .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, @@ -1332,7 +1431,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, - .teardown.single = NULL, + .teardown.single = smpboot_park_threads, }, [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { .name = "irq/affinity:online", @@ -1344,6 +1443,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, + [CPUHP_AP_WATCHDOG_ONLINE] = { + .name = "lockup_detector:online", + .startup.single = lockup_detector_online_cpu, + .teardown.single = lockup_detector_offline_cpu, + }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, @@ -1906,10 +2010,172 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = { NULL }; +#ifdef CONFIG_HOTPLUG_SMT + +static const char *smt_states[] = { + [CPU_SMT_ENABLED] = "on", + [CPU_SMT_DISABLED] = "off", + [CPU_SMT_FORCE_DISABLED] = "forceoff", + [CPU_SMT_NOT_SUPPORTED] = "notsupported", +}; + +static ssize_t +show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) +{ + return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]); +} + +static void cpuhp_offline_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = true; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); +} + +static void cpuhp_online_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = false; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_ONLINE); +} + +static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + for_each_online_cpu(cpu) { + if (topology_is_primary_thread(cpu)) + continue; + ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); + if (ret) + break; + /* + * As this needs to hold the cpu maps lock it's impossible + * to call device_offline() because that ends up calling + * cpu_down() which takes cpu maps lock. cpu maps lock + * needs to be held as this might race against in kernel + * abusers of the hotplug machinery (thermal management). + * + * So nothing would update device:offline state. That would + * leave the sysfs entry stale and prevent onlining after + * smt control has been changed to 'off' again. This is + * called under the sysfs hotplug lock, so it is properly + * serialized against the regular offline usage. + */ + cpuhp_offline_cpu_device(cpu); + } + if (!ret) + cpu_smt_control = ctrlval; + cpu_maps_update_done(); + return ret; +} + +static int cpuhp_smt_enable(void) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + cpu_smt_control = CPU_SMT_ENABLED; + for_each_present_cpu(cpu) { + /* Skip online CPUs and CPUs on offline nodes */ + if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) + continue; + ret = _cpu_up(cpu, 0, CPUHP_ONLINE); + if (ret) + break; + /* See comment in cpuhp_smt_disable() */ + cpuhp_online_cpu_device(cpu); + } + cpu_maps_update_done(); + return ret; +} + +static ssize_t +store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int ctrlval, ret; + + if (sysfs_streq(buf, "on")) + ctrlval = CPU_SMT_ENABLED; + else if (sysfs_streq(buf, "off")) + ctrlval = CPU_SMT_DISABLED; + else if (sysfs_streq(buf, "forceoff")) + ctrlval = CPU_SMT_FORCE_DISABLED; + else + return -EINVAL; + + if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) + return -EPERM; + + if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) + return -ENODEV; + + ret = lock_device_hotplug_sysfs(); + if (ret) + return ret; + + if (ctrlval != cpu_smt_control) { + switch (ctrlval) { + case CPU_SMT_ENABLED: + ret = cpuhp_smt_enable(); + break; + case CPU_SMT_DISABLED: + case CPU_SMT_FORCE_DISABLED: + ret = cpuhp_smt_disable(ctrlval); + break; + } + } + + unlock_device_hotplug(); + return ret ? ret : count; +} +static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control); + +static ssize_t +show_smt_active(struct device *dev, struct device_attribute *attr, char *buf) +{ + bool active = topology_max_smt_threads() > 1; + + return snprintf(buf, PAGE_SIZE - 2, "%d\n", active); +} +static DEVICE_ATTR(active, 0444, show_smt_active, NULL); + +static struct attribute *cpuhp_smt_attrs[] = { + &dev_attr_control.attr, + &dev_attr_active.attr, + NULL +}; + +static const struct attribute_group cpuhp_smt_attr_group = { + .attrs = cpuhp_smt_attrs, + .name = "smt", + NULL +}; + +static int __init cpu_smt_state_init(void) +{ + return sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpuhp_smt_attr_group); +} + +#else +static inline int cpu_smt_state_init(void) { return 0; } +#endif + static int __init cpuhp_sysfs_init(void) { int cpu, ret; + ret = cpu_smt_state_init(); + if (ret) + return ret; + ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_cpu_root_attr_group); if (ret) @@ -2010,7 +2276,10 @@ void __init boot_cpu_init(void) /* * Must be called _AFTER_ setting up the per_cpu areas */ -void __init boot_cpu_state_init(void) +void __init boot_cpu_hotplug_init(void) { - per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE; +#ifdef CONFIG_SMP + this_cpu_write(cpuhp_state.booted_once, true); +#endif + this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } diff --git a/kernel/crash_core.c b/kernel/crash_core.c index f7674d676889..b66aced5e8c2 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -460,6 +460,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_hwpoison); #endif VMCOREINFO_NUMBER(PG_head_mask); +#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); #ifdef CONFIG_HUGETLB_PAGE VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index e405677ee08d..2ddfce8f1e8f 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -691,7 +691,7 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0) } if (!s->usable) return KDB_NOTIMP; - s->command = kzalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB); + s->command = kcalloc(s->count + 1, sizeof(*(s->command)), GFP_KDB); if (!s->command) { kdb_printf("Could not allocate new kdb_defcmd table for %s\n", cmdstr); @@ -729,8 +729,8 @@ static int kdb_defcmd(int argc, const char **argv) kdb_printf("Command only available during kdb_init()\n"); return KDB_NOTIMP; } - defcmd_set = kmalloc((defcmd_set_count + 1) * sizeof(*defcmd_set), - GFP_KDB); + defcmd_set = kmalloc_array(defcmd_set_count + 1, sizeof(*defcmd_set), + GFP_KDB); if (!defcmd_set) goto fail_defcmd; memcpy(defcmd_set, save_defcmd_set, @@ -2706,8 +2706,11 @@ int kdb_register_flags(char *cmd, } if (i >= kdb_max_commands) { - kdbtab_t *new = kmalloc((kdb_max_commands - KDB_BASE_CMD_MAX + - kdb_command_extend) * sizeof(*new), GFP_KDB); + kdbtab_t *new = kmalloc_array(kdb_max_commands - + KDB_BASE_CMD_MAX + + kdb_command_extend, + sizeof(*new), + GFP_KDB); if (!new) { kdb_printf("Could not allocate new kdb_command " "table\n"); diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig new file mode 100644 index 000000000000..9bd54304446f --- /dev/null +++ b/kernel/dma/Kconfig @@ -0,0 +1,50 @@ + +config HAS_DMA + bool + depends on !NO_DMA + default y + +config NEED_SG_DMA_LENGTH + bool + +config NEED_DMA_MAP_STATE + bool + +config ARCH_DMA_ADDR_T_64BIT + def_bool 64BIT || PHYS_ADDR_T_64BIT + +config HAVE_GENERIC_DMA_COHERENT + bool + +config ARCH_HAS_SYNC_DMA_FOR_DEVICE + bool + +config ARCH_HAS_SYNC_DMA_FOR_CPU + bool + select NEED_DMA_MAP_STATE + +config DMA_DIRECT_OPS + bool + depends on HAS_DMA + +config DMA_NONCOHERENT_OPS + bool + depends on HAS_DMA + select DMA_DIRECT_OPS + +config DMA_NONCOHERENT_MMAP + bool + depends on DMA_NONCOHERENT_OPS + +config DMA_NONCOHERENT_CACHE_SYNC + bool + depends on DMA_NONCOHERENT_OPS + +config DMA_VIRT_OPS + bool + depends on HAS_DMA + +config SWIOTLB + bool + select DMA_DIRECT_OPS + select NEED_DMA_MAP_STATE diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile new file mode 100644 index 000000000000..6de44e4eb454 --- /dev/null +++ b/kernel/dma/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_HAS_DMA) += mapping.o +obj-$(CONFIG_DMA_CMA) += contiguous.o +obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o +obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o +obj-$(CONFIG_DMA_NONCOHERENT_OPS) += noncoherent.o +obj-$(CONFIG_DMA_VIRT_OPS) += virt.o +obj-$(CONFIG_DMA_API_DEBUG) += debug.o +obj-$(CONFIG_SWIOTLB) += swiotlb.o + diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c new file mode 100644 index 000000000000..597d40893862 --- /dev/null +++ b/kernel/dma/coherent.c @@ -0,0 +1,434 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Coherent per-device memory handling. + * Borrowed from i386 + */ +#include <linux/io.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/dma-mapping.h> + +struct dma_coherent_mem { + void *virt_base; + dma_addr_t device_base; + unsigned long pfn_base; + int size; + int flags; + unsigned long *bitmap; + spinlock_t spinlock; + bool use_dev_dma_pfn_offset; +}; + +static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init; + +static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev) +{ + if (dev && dev->dma_mem) + return dev->dma_mem; + return NULL; +} + +static inline dma_addr_t dma_get_device_base(struct device *dev, + struct dma_coherent_mem * mem) +{ + if (mem->use_dev_dma_pfn_offset) + return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT; + else + return mem->device_base; +} + +static int dma_init_coherent_memory( + phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags, + struct dma_coherent_mem **mem) +{ + struct dma_coherent_mem *dma_mem = NULL; + void __iomem *mem_base = NULL; + int pages = size >> PAGE_SHIFT; + int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long); + int ret; + + if (!size) { + ret = -EINVAL; + goto out; + } + + mem_base = memremap(phys_addr, size, MEMREMAP_WC); + if (!mem_base) { + ret = -EINVAL; + goto out; + } + dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); + if (!dma_mem) { + ret = -ENOMEM; + goto out; + } + dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!dma_mem->bitmap) { + ret = -ENOMEM; + goto out; + } + + dma_mem->virt_base = mem_base; + dma_mem->device_base = device_addr; + dma_mem->pfn_base = PFN_DOWN(phys_addr); + dma_mem->size = pages; + dma_mem->flags = flags; + spin_lock_init(&dma_mem->spinlock); + + *mem = dma_mem; + return 0; + +out: + kfree(dma_mem); + if (mem_base) + memunmap(mem_base); + return ret; +} + +static void dma_release_coherent_memory(struct dma_coherent_mem *mem) +{ + if (!mem) + return; + + memunmap(mem->virt_base); + kfree(mem->bitmap); + kfree(mem); +} + +static int dma_assign_coherent_memory(struct device *dev, + struct dma_coherent_mem *mem) +{ + if (!dev) + return -ENODEV; + + if (dev->dma_mem) + return -EBUSY; + + dev->dma_mem = mem; + return 0; +} + +int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, + dma_addr_t device_addr, size_t size, int flags) +{ + struct dma_coherent_mem *mem; + int ret; + + ret = dma_init_coherent_memory(phys_addr, device_addr, size, flags, &mem); + if (ret) + return ret; + + ret = dma_assign_coherent_memory(dev, mem); + if (ret) + dma_release_coherent_memory(mem); + return ret; +} +EXPORT_SYMBOL(dma_declare_coherent_memory); + +void dma_release_declared_memory(struct device *dev) +{ + struct dma_coherent_mem *mem = dev->dma_mem; + + if (!mem) + return; + dma_release_coherent_memory(mem); + dev->dma_mem = NULL; +} +EXPORT_SYMBOL(dma_release_declared_memory); + +void *dma_mark_declared_memory_occupied(struct device *dev, + dma_addr_t device_addr, size_t size) +{ + struct dma_coherent_mem *mem = dev->dma_mem; + unsigned long flags; + int pos, err; + + size += device_addr & ~PAGE_MASK; + + if (!mem) + return ERR_PTR(-EINVAL); + + spin_lock_irqsave(&mem->spinlock, flags); + pos = PFN_DOWN(device_addr - dma_get_device_base(dev, mem)); + err = bitmap_allocate_region(mem->bitmap, pos, get_order(size)); + spin_unlock_irqrestore(&mem->spinlock, flags); + + if (err != 0) + return ERR_PTR(err); + return mem->virt_base + (pos << PAGE_SHIFT); +} +EXPORT_SYMBOL(dma_mark_declared_memory_occupied); + +static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem, + ssize_t size, dma_addr_t *dma_handle) +{ + int order = get_order(size); + unsigned long flags; + int pageno; + void *ret; + + spin_lock_irqsave(&mem->spinlock, flags); + + if (unlikely(size > (mem->size << PAGE_SHIFT))) + goto err; + + pageno = bitmap_find_free_region(mem->bitmap, mem->size, order); + if (unlikely(pageno < 0)) + goto err; + + /* + * Memory was found in the coherent area. + */ + *dma_handle = mem->device_base + (pageno << PAGE_SHIFT); + ret = mem->virt_base + (pageno << PAGE_SHIFT); + spin_unlock_irqrestore(&mem->spinlock, flags); + memset(ret, 0, size); + return ret; +err: + spin_unlock_irqrestore(&mem->spinlock, flags); + return NULL; +} + +/** + * dma_alloc_from_dev_coherent() - allocate memory from device coherent pool + * @dev: device from which we allocate memory + * @size: size of requested memory area + * @dma_handle: This will be filled with the correct dma handle + * @ret: This pointer will be filled with the virtual address + * to allocated area. + * + * This function should be only called from per-arch dma_alloc_coherent() + * to support allocation from per-device coherent memory pools. + * + * Returns 0 if dma_alloc_coherent should continue with allocating from + * generic memory areas, or !0 if dma_alloc_coherent should return @ret. + */ +int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle, void **ret) +{ + struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); + + if (!mem) + return 0; + + *ret = __dma_alloc_from_coherent(mem, size, dma_handle); + if (*ret) + return 1; + + /* + * In the case where the allocation can not be satisfied from the + * per-device area, try to fall back to generic memory if the + * constraints allow it. + */ + return mem->flags & DMA_MEMORY_EXCLUSIVE; +} +EXPORT_SYMBOL(dma_alloc_from_dev_coherent); + +void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle) +{ + if (!dma_coherent_default_memory) + return NULL; + + return __dma_alloc_from_coherent(dma_coherent_default_memory, size, + dma_handle); +} + +static int __dma_release_from_coherent(struct dma_coherent_mem *mem, + int order, void *vaddr) +{ + if (mem && vaddr >= mem->virt_base && vaddr < + (mem->virt_base + (mem->size << PAGE_SHIFT))) { + int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; + unsigned long flags; + + spin_lock_irqsave(&mem->spinlock, flags); + bitmap_release_region(mem->bitmap, page, order); + spin_unlock_irqrestore(&mem->spinlock, flags); + return 1; + } + return 0; +} + +/** + * dma_release_from_dev_coherent() - free memory to device coherent memory pool + * @dev: device from which the memory was allocated + * @order: the order of pages allocated + * @vaddr: virtual address of allocated pages + * + * This checks whether the memory was allocated from the per-device + * coherent memory pool and if so, releases that memory. + * + * Returns 1 if we correctly released the memory, or 0 if the caller should + * proceed with releasing memory from generic pools. + */ +int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr) +{ + struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); + + return __dma_release_from_coherent(mem, order, vaddr); +} +EXPORT_SYMBOL(dma_release_from_dev_coherent); + +int dma_release_from_global_coherent(int order, void *vaddr) +{ + if (!dma_coherent_default_memory) + return 0; + + return __dma_release_from_coherent(dma_coherent_default_memory, order, + vaddr); +} + +static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem, + struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) +{ + if (mem && vaddr >= mem->virt_base && vaddr + size <= + (mem->virt_base + (mem->size << PAGE_SHIFT))) { + unsigned long off = vma->vm_pgoff; + int start = (vaddr - mem->virt_base) >> PAGE_SHIFT; + int user_count = vma_pages(vma); + int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + *ret = -ENXIO; + if (off < count && user_count <= count - off) { + unsigned long pfn = mem->pfn_base + start + off; + *ret = remap_pfn_range(vma, vma->vm_start, pfn, + user_count << PAGE_SHIFT, + vma->vm_page_prot); + } + return 1; + } + return 0; +} + +/** + * dma_mmap_from_dev_coherent() - mmap memory from the device coherent pool + * @dev: device from which the memory was allocated + * @vma: vm_area for the userspace memory + * @vaddr: cpu address returned by dma_alloc_from_dev_coherent + * @size: size of the memory buffer allocated + * @ret: result from remap_pfn_range() + * + * This checks whether the memory was allocated from the per-device + * coherent memory pool and if so, maps that memory to the provided vma. + * + * Returns 1 if @vaddr belongs to the device coherent pool and the caller + * should return @ret, or 0 if they should proceed with mapping memory from + * generic areas. + */ +int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, + void *vaddr, size_t size, int *ret) +{ + struct dma_coherent_mem *mem = dev_get_coherent_memory(dev); + + return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret); +} +EXPORT_SYMBOL(dma_mmap_from_dev_coherent); + +int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr, + size_t size, int *ret) +{ + if (!dma_coherent_default_memory) + return 0; + + return __dma_mmap_from_coherent(dma_coherent_default_memory, vma, + vaddr, size, ret); +} + +/* + * Support for reserved memory regions defined in device tree + */ +#ifdef CONFIG_OF_RESERVED_MEM +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/of_reserved_mem.h> + +static struct reserved_mem *dma_reserved_default_memory __initdata; + +static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev) +{ + struct dma_coherent_mem *mem = rmem->priv; + int ret; + + if (!mem) { + ret = dma_init_coherent_memory(rmem->base, rmem->base, + rmem->size, + DMA_MEMORY_EXCLUSIVE, &mem); + if (ret) { + pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n", + &rmem->base, (unsigned long)rmem->size / SZ_1M); + return ret; + } + } + mem->use_dev_dma_pfn_offset = true; + rmem->priv = mem; + dma_assign_coherent_memory(dev, mem); + return 0; +} + +static void rmem_dma_device_release(struct reserved_mem *rmem, + struct device *dev) +{ + if (dev) + dev->dma_mem = NULL; +} + +static const struct reserved_mem_ops rmem_dma_ops = { + .device_init = rmem_dma_device_init, + .device_release = rmem_dma_device_release, +}; + +static int __init rmem_dma_setup(struct reserved_mem *rmem) +{ + unsigned long node = rmem->fdt_node; + + if (of_get_flat_dt_prop(node, "reusable", NULL)) + return -EINVAL; + +#ifdef CONFIG_ARM + if (!of_get_flat_dt_prop(node, "no-map", NULL)) { + pr_err("Reserved memory: regions without no-map are not yet supported\n"); + return -EINVAL; + } + + if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) { + WARN(dma_reserved_default_memory, + "Reserved memory: region for default DMA coherent area is redefined\n"); + dma_reserved_default_memory = rmem; + } +#endif + + rmem->ops = &rmem_dma_ops; + pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n", + &rmem->base, (unsigned long)rmem->size / SZ_1M); + return 0; +} + +static int __init dma_init_reserved_memory(void) +{ + const struct reserved_mem_ops *ops; + int ret; + + if (!dma_reserved_default_memory) + return -ENOMEM; + + ops = dma_reserved_default_memory->ops; + + /* + * We rely on rmem_dma_device_init() does not propagate error of + * dma_assign_coherent_memory() for "NULL" device. + */ + ret = ops->device_init(dma_reserved_default_memory, NULL); + + if (!ret) { + dma_coherent_default_memory = dma_reserved_default_memory->priv; + pr_info("DMA: default coherent area is set\n"); + } + + return ret; +} + +core_initcall(dma_init_reserved_memory); + +RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup); +#endif diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c new file mode 100644 index 000000000000..d987dcd1bd56 --- /dev/null +++ b/kernel/dma/contiguous.c @@ -0,0 +1,278 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski <m.szyprowski@samsung.com> + * Michal Nazarewicz <mina86@mina86.com> + */ + +#define pr_fmt(fmt) "cma: " fmt + +#ifdef CONFIG_CMA_DEBUG +#ifndef DEBUG +# define DEBUG +#endif +#endif + +#include <asm/page.h> +#include <asm/dma-contiguous.h> + +#include <linux/memblock.h> +#include <linux/err.h> +#include <linux/sizes.h> +#include <linux/dma-contiguous.h> +#include <linux/cma.h> + +#ifdef CONFIG_CMA_SIZE_MBYTES +#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES +#else +#define CMA_SIZE_MBYTES 0 +#endif + +struct cma *dma_contiguous_default_area; + +/* + * Default global CMA area size can be defined in kernel's .config. + * This is useful mainly for distro maintainers to create a kernel + * that works correctly for most supported systems. + * The size can be set in bytes or as a percentage of the total memory + * in the system. + * + * Users, who want to set the size of global CMA area for their system + * should use cma= kernel parameter. + */ +static const phys_addr_t size_bytes = (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M; +static phys_addr_t size_cmdline = -1; +static phys_addr_t base_cmdline; +static phys_addr_t limit_cmdline; + +static int __init early_cma(char *p) +{ + pr_debug("%s(%s)\n", __func__, p); + size_cmdline = memparse(p, &p); + if (*p != '@') + return 0; + base_cmdline = memparse(p + 1, &p); + if (*p != '-') { + limit_cmdline = base_cmdline + size_cmdline; + return 0; + } + limit_cmdline = memparse(p + 1, &p); + + return 0; +} +early_param("cma", early_cma); + +#ifdef CONFIG_CMA_SIZE_PERCENTAGE + +static phys_addr_t __init __maybe_unused cma_early_percent_memory(void) +{ + struct memblock_region *reg; + unsigned long total_pages = 0; + + /* + * We cannot use memblock_phys_mem_size() here, because + * memblock_analyze() has not been called yet. + */ + for_each_memblock(memory, reg) + total_pages += memblock_region_memory_end_pfn(reg) - + memblock_region_memory_base_pfn(reg); + + return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT; +} + +#else + +static inline __maybe_unused phys_addr_t cma_early_percent_memory(void) +{ + return 0; +} + +#endif + +/** + * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. + */ +void __init dma_contiguous_reserve(phys_addr_t limit) +{ + phys_addr_t selected_size = 0; + phys_addr_t selected_base = 0; + phys_addr_t selected_limit = limit; + bool fixed = false; + + pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); + + if (size_cmdline != -1) { + selected_size = size_cmdline; + selected_base = base_cmdline; + selected_limit = min_not_zero(limit_cmdline, limit); + if (base_cmdline + size_cmdline == limit_cmdline) + fixed = true; + } else { +#ifdef CONFIG_CMA_SIZE_SEL_MBYTES + selected_size = size_bytes; +#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE) + selected_size = cma_early_percent_memory(); +#elif defined(CONFIG_CMA_SIZE_SEL_MIN) + selected_size = min(size_bytes, cma_early_percent_memory()); +#elif defined(CONFIG_CMA_SIZE_SEL_MAX) + selected_size = max(size_bytes, cma_early_percent_memory()); +#endif + } + + if (selected_size && !dma_contiguous_default_area) { + pr_debug("%s: reserving %ld MiB for global area\n", __func__, + (unsigned long)selected_size / SZ_1M); + + dma_contiguous_reserve_area(selected_size, selected_base, + selected_limit, + &dma_contiguous_default_area, + fixed); + } +} + +/** + * dma_contiguous_reserve_area() - reserve custom contiguous area + * @size: Size of the reserved area (in bytes), + * @base: Base address of the reserved area optional, use 0 for any + * @limit: End address of the reserved memory (optional, 0 for any). + * @res_cma: Pointer to store the created cma region. + * @fixed: hint about where to place the reserved area + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. This function allows to create custom reserved areas for specific + * devices. + * + * If @fixed is true, reserve contiguous area at exactly @base. If false, + * reserve in range from @base to @limit. + */ +int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, + phys_addr_t limit, struct cma **res_cma, + bool fixed) +{ + int ret; + + ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed, + "reserved", res_cma); + if (ret) + return ret; + + /* Architecture specific contiguous memory fixup. */ + dma_contiguous_early_fixup(cma_get_base(*res_cma), + cma_get_size(*res_cma)); + + return 0; +} + +/** + * dma_alloc_from_contiguous() - allocate pages from contiguous area + * @dev: Pointer to device for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * @gfp_mask: GFP flags to use for this allocation. + * + * This function allocates memory buffer for specified device. It uses + * device specific contiguous memory area if available or the default + * global one. Requires architecture specific dev_get_cma_area() helper + * function. + */ +struct page *dma_alloc_from_contiguous(struct device *dev, size_t count, + unsigned int align, gfp_t gfp_mask) +{ + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + return cma_alloc(dev_get_cma_area(dev), count, align, gfp_mask); +} + +/** + * dma_release_from_contiguous() - release allocated pages + * @dev: Pointer to device for which the pages were allocated. + * @pages: Allocated pages. + * @count: Number of allocated pages. + * + * This function releases memory allocated by dma_alloc_from_contiguous(). + * It returns false when provided pages do not belong to contiguous area and + * true otherwise. + */ +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + return cma_release(dev_get_cma_area(dev), pages, count); +} + +/* + * Support for reserved memory regions defined in device tree + */ +#ifdef CONFIG_OF_RESERVED_MEM +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/of_reserved_mem.h> + +#undef pr_fmt +#define pr_fmt(fmt) fmt + +static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev) +{ + dev_set_cma_area(dev, rmem->priv); + return 0; +} + +static void rmem_cma_device_release(struct reserved_mem *rmem, + struct device *dev) +{ + dev_set_cma_area(dev, NULL); +} + +static const struct reserved_mem_ops rmem_cma_ops = { + .device_init = rmem_cma_device_init, + .device_release = rmem_cma_device_release, +}; + +static int __init rmem_cma_setup(struct reserved_mem *rmem) +{ + phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); + phys_addr_t mask = align - 1; + unsigned long node = rmem->fdt_node; + struct cma *cma; + int err; + + if (!of_get_flat_dt_prop(node, "reusable", NULL) || + of_get_flat_dt_prop(node, "no-map", NULL)) + return -EINVAL; + + if ((rmem->base & mask) || (rmem->size & mask)) { + pr_err("Reserved memory: incorrect alignment of CMA region\n"); + return -EINVAL; + } + + err = cma_init_reserved_mem(rmem->base, rmem->size, 0, rmem->name, &cma); + if (err) { + pr_err("Reserved memory: unable to setup CMA region\n"); + return err; + } + /* Architecture specific contiguous memory fixup. */ + dma_contiguous_early_fixup(rmem->base, rmem->size); + + if (of_get_flat_dt_prop(node, "linux,cma-default", NULL)) + dma_contiguous_set_default(cma); + + rmem->ops = &rmem_cma_ops; + rmem->priv = cma; + + pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n", + &rmem->base, (unsigned long)rmem->size / SZ_1M); + + return 0; +} +RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup); +#endif diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c new file mode 100644 index 000000000000..c007d25bee09 --- /dev/null +++ b/kernel/dma/debug.c @@ -0,0 +1,1773 @@ +/* + * Copyright (C) 2008 Advanced Micro Devices, Inc. + * + * Author: Joerg Roedel <joerg.roedel@amd.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/sched/task_stack.h> +#include <linux/scatterlist.h> +#include <linux/dma-mapping.h> +#include <linux/sched/task.h> +#include <linux/stacktrace.h> +#include <linux/dma-debug.h> +#include <linux/spinlock.h> +#include <linux/vmalloc.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/export.h> +#include <linux/device.h> +#include <linux/types.h> +#include <linux/sched.h> +#include <linux/ctype.h> +#include <linux/list.h> +#include <linux/slab.h> + +#include <asm/sections.h> + +#define HASH_SIZE 1024ULL +#define HASH_FN_SHIFT 13 +#define HASH_FN_MASK (HASH_SIZE - 1) + +/* allow architectures to override this if absolutely required */ +#ifndef PREALLOC_DMA_DEBUG_ENTRIES +#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) +#endif + +enum { + dma_debug_single, + dma_debug_page, + dma_debug_sg, + dma_debug_coherent, + dma_debug_resource, +}; + +enum map_err_types { + MAP_ERR_CHECK_NOT_APPLICABLE, + MAP_ERR_NOT_CHECKED, + MAP_ERR_CHECKED, +}; + +#define DMA_DEBUG_STACKTRACE_ENTRIES 5 + +/** + * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping + * @list: node on pre-allocated free_entries list + * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent + * @type: single, page, sg, coherent + * @pfn: page frame of the start address + * @offset: offset of mapping relative to pfn + * @size: length of the mapping + * @direction: enum dma_data_direction + * @sg_call_ents: 'nents' from dma_map_sg + * @sg_mapped_ents: 'mapped_ents' from dma_map_sg + * @map_err_type: track whether dma_mapping_error() was checked + * @stacktrace: support backtraces when a violation is detected + */ +struct dma_debug_entry { + struct list_head list; + struct device *dev; + int type; + unsigned long pfn; + size_t offset; + u64 dev_addr; + u64 size; + int direction; + int sg_call_ents; + int sg_mapped_ents; + enum map_err_types map_err_type; +#ifdef CONFIG_STACKTRACE + struct stack_trace stacktrace; + unsigned long st_entries[DMA_DEBUG_STACKTRACE_ENTRIES]; +#endif +}; + +typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *); + +struct hash_bucket { + struct list_head list; + spinlock_t lock; +} ____cacheline_aligned_in_smp; + +/* Hash list to save the allocated dma addresses */ +static struct hash_bucket dma_entry_hash[HASH_SIZE]; +/* List of pre-allocated dma_debug_entry's */ +static LIST_HEAD(free_entries); +/* Lock for the list above */ +static DEFINE_SPINLOCK(free_entries_lock); + +/* Global disable flag - will be set in case of an error */ +static bool global_disable __read_mostly; + +/* Early initialization disable flag, set at the end of dma_debug_init */ +static bool dma_debug_initialized __read_mostly; + +static inline bool dma_debug_disabled(void) +{ + return global_disable || !dma_debug_initialized; +} + +/* Global error count */ +static u32 error_count; + +/* Global error show enable*/ +static u32 show_all_errors __read_mostly; +/* Number of errors to show */ +static u32 show_num_errors = 1; + +static u32 num_free_entries; +static u32 min_free_entries; +static u32 nr_total_entries; + +/* number of preallocated entries requested by kernel cmdline */ +static u32 nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES; + +/* debugfs dentry's for the stuff above */ +static struct dentry *dma_debug_dent __read_mostly; +static struct dentry *global_disable_dent __read_mostly; +static struct dentry *error_count_dent __read_mostly; +static struct dentry *show_all_errors_dent __read_mostly; +static struct dentry *show_num_errors_dent __read_mostly; +static struct dentry *num_free_entries_dent __read_mostly; +static struct dentry *min_free_entries_dent __read_mostly; +static struct dentry *filter_dent __read_mostly; + +/* per-driver filter related state */ + +#define NAME_MAX_LEN 64 + +static char current_driver_name[NAME_MAX_LEN] __read_mostly; +static struct device_driver *current_driver __read_mostly; + +static DEFINE_RWLOCK(driver_name_lock); + +static const char *const maperr2str[] = { + [MAP_ERR_CHECK_NOT_APPLICABLE] = "dma map error check not applicable", + [MAP_ERR_NOT_CHECKED] = "dma map error not checked", + [MAP_ERR_CHECKED] = "dma map error checked", +}; + +static const char *type2name[5] = { "single", "page", + "scather-gather", "coherent", + "resource" }; + +static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE", + "DMA_FROM_DEVICE", "DMA_NONE" }; + +/* + * The access to some variables in this macro is racy. We can't use atomic_t + * here because all these variables are exported to debugfs. Some of them even + * writeable. This is also the reason why a lock won't help much. But anyway, + * the races are no big deal. Here is why: + * + * error_count: the addition is racy, but the worst thing that can happen is + * that we don't count some errors + * show_num_errors: the subtraction is racy. Also no big deal because in + * worst case this will result in one warning more in the + * system log than the user configured. This variable is + * writeable via debugfs. + */ +static inline void dump_entry_trace(struct dma_debug_entry *entry) +{ +#ifdef CONFIG_STACKTRACE + if (entry) { + pr_warning("Mapped at:\n"); + print_stack_trace(&entry->stacktrace, 0); + } +#endif +} + +static bool driver_filter(struct device *dev) +{ + struct device_driver *drv; + unsigned long flags; + bool ret; + + /* driver filter off */ + if (likely(!current_driver_name[0])) + return true; + + /* driver filter on and initialized */ + if (current_driver && dev && dev->driver == current_driver) + return true; + + /* driver filter on, but we can't filter on a NULL device... */ + if (!dev) + return false; + + if (current_driver || !current_driver_name[0]) + return false; + + /* driver filter on but not yet initialized */ + drv = dev->driver; + if (!drv) + return false; + + /* lock to protect against change of current_driver_name */ + read_lock_irqsave(&driver_name_lock, flags); + + ret = false; + if (drv->name && + strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) { + current_driver = drv; + ret = true; + } + + read_unlock_irqrestore(&driver_name_lock, flags); + + return ret; +} + +#define err_printk(dev, entry, format, arg...) do { \ + error_count += 1; \ + if (driver_filter(dev) && \ + (show_all_errors || show_num_errors > 0)) { \ + WARN(1, "%s %s: " format, \ + dev ? dev_driver_string(dev) : "NULL", \ + dev ? dev_name(dev) : "NULL", ## arg); \ + dump_entry_trace(entry); \ + } \ + if (!show_all_errors && show_num_errors > 0) \ + show_num_errors -= 1; \ + } while (0); + +/* + * Hash related functions + * + * Every DMA-API request is saved into a struct dma_debug_entry. To + * have quick access to these structs they are stored into a hash. + */ +static int hash_fn(struct dma_debug_entry *entry) +{ + /* + * Hash function is based on the dma address. + * We use bits 20-27 here as the index into the hash + */ + return (entry->dev_addr >> HASH_FN_SHIFT) & HASH_FN_MASK; +} + +/* + * Request exclusive access to a hash bucket for a given dma_debug_entry. + */ +static struct hash_bucket *get_hash_bucket(struct dma_debug_entry *entry, + unsigned long *flags) + __acquires(&dma_entry_hash[idx].lock) +{ + int idx = hash_fn(entry); + unsigned long __flags; + + spin_lock_irqsave(&dma_entry_hash[idx].lock, __flags); + *flags = __flags; + return &dma_entry_hash[idx]; +} + +/* + * Give up exclusive access to the hash bucket + */ +static void put_hash_bucket(struct hash_bucket *bucket, + unsigned long *flags) + __releases(&bucket->lock) +{ + unsigned long __flags = *flags; + + spin_unlock_irqrestore(&bucket->lock, __flags); +} + +static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b) +{ + return ((a->dev_addr == b->dev_addr) && + (a->dev == b->dev)) ? true : false; +} + +static bool containing_match(struct dma_debug_entry *a, + struct dma_debug_entry *b) +{ + if (a->dev != b->dev) + return false; + + if ((b->dev_addr <= a->dev_addr) && + ((b->dev_addr + b->size) >= (a->dev_addr + a->size))) + return true; + + return false; +} + +/* + * Search a given entry in the hash bucket list + */ +static struct dma_debug_entry *__hash_bucket_find(struct hash_bucket *bucket, + struct dma_debug_entry *ref, + match_fn match) +{ + struct dma_debug_entry *entry, *ret = NULL; + int matches = 0, match_lvl, last_lvl = -1; + + list_for_each_entry(entry, &bucket->list, list) { + if (!match(ref, entry)) + continue; + + /* + * Some drivers map the same physical address multiple + * times. Without a hardware IOMMU this results in the + * same device addresses being put into the dma-debug + * hash multiple times too. This can result in false + * positives being reported. Therefore we implement a + * best-fit algorithm here which returns the entry from + * the hash which fits best to the reference value + * instead of the first-fit. + */ + matches += 1; + match_lvl = 0; + entry->size == ref->size ? ++match_lvl : 0; + entry->type == ref->type ? ++match_lvl : 0; + entry->direction == ref->direction ? ++match_lvl : 0; + entry->sg_call_ents == ref->sg_call_ents ? ++match_lvl : 0; + + if (match_lvl == 4) { + /* perfect-fit - return the result */ + return entry; + } else if (match_lvl > last_lvl) { + /* + * We found an entry that fits better then the + * previous one or it is the 1st match. + */ + last_lvl = match_lvl; + ret = entry; + } + } + + /* + * If we have multiple matches but no perfect-fit, just return + * NULL. + */ + ret = (matches == 1) ? ret : NULL; + + return ret; +} + +static struct dma_debug_entry *bucket_find_exact(struct hash_bucket *bucket, + struct dma_debug_entry *ref) +{ + return __hash_bucket_find(bucket, ref, exact_match); +} + +static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket, + struct dma_debug_entry *ref, + unsigned long *flags) +{ + + unsigned int max_range = dma_get_max_seg_size(ref->dev); + struct dma_debug_entry *entry, index = *ref; + unsigned int range = 0; + + while (range <= max_range) { + entry = __hash_bucket_find(*bucket, ref, containing_match); + + if (entry) + return entry; + + /* + * Nothing found, go back a hash bucket + */ + put_hash_bucket(*bucket, flags); + range += (1 << HASH_FN_SHIFT); + index.dev_addr -= (1 << HASH_FN_SHIFT); + *bucket = get_hash_bucket(&index, flags); + } + + return NULL; +} + +/* + * Add an entry to a hash bucket + */ +static void hash_bucket_add(struct hash_bucket *bucket, + struct dma_debug_entry *entry) +{ + list_add_tail(&entry->list, &bucket->list); +} + +/* + * Remove entry from a hash bucket list + */ +static void hash_bucket_del(struct dma_debug_entry *entry) +{ + list_del(&entry->list); +} + +static unsigned long long phys_addr(struct dma_debug_entry *entry) +{ + if (entry->type == dma_debug_resource) + return __pfn_to_phys(entry->pfn) + entry->offset; + + return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset; +} + +/* + * Dump mapping entries for debugging purposes + */ +void debug_dma_dump_mappings(struct device *dev) +{ + int idx; + + for (idx = 0; idx < HASH_SIZE; idx++) { + struct hash_bucket *bucket = &dma_entry_hash[idx]; + struct dma_debug_entry *entry; + unsigned long flags; + + spin_lock_irqsave(&bucket->lock, flags); + + list_for_each_entry(entry, &bucket->list, list) { + if (!dev || dev == entry->dev) { + dev_info(entry->dev, + "%s idx %d P=%Lx N=%lx D=%Lx L=%Lx %s %s\n", + type2name[entry->type], idx, + phys_addr(entry), entry->pfn, + entry->dev_addr, entry->size, + dir2name[entry->direction], + maperr2str[entry->map_err_type]); + } + } + + spin_unlock_irqrestore(&bucket->lock, flags); + } +} + +/* + * For each mapping (initial cacheline in the case of + * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a + * scatterlist, or the cacheline specified in dma_map_single) insert + * into this tree using the cacheline as the key. At + * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry. If + * the entry already exists at insertion time add a tag as a reference + * count for the overlapping mappings. For now, the overlap tracking + * just ensures that 'unmaps' balance 'maps' before marking the + * cacheline idle, but we should also be flagging overlaps as an API + * violation. + * + * Memory usage is mostly constrained by the maximum number of available + * dma-debug entries in that we need a free dma_debug_entry before + * inserting into the tree. In the case of dma_map_page and + * dma_alloc_coherent there is only one dma_debug_entry and one + * dma_active_cacheline entry to track per event. dma_map_sg(), on the + * other hand, consumes a single dma_debug_entry, but inserts 'nents' + * entries into the tree. + * + * At any time debug_dma_assert_idle() can be called to trigger a + * warning if any cachelines in the given page are in the active set. + */ +static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT); +static DEFINE_SPINLOCK(radix_lock); +#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1) +#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT) +#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT) + +static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry) +{ + return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) + + (entry->offset >> L1_CACHE_SHIFT); +} + +static int active_cacheline_read_overlap(phys_addr_t cln) +{ + int overlap = 0, i; + + for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) + if (radix_tree_tag_get(&dma_active_cacheline, cln, i)) + overlap |= 1 << i; + return overlap; +} + +static int active_cacheline_set_overlap(phys_addr_t cln, int overlap) +{ + int i; + + if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0) + return overlap; + + for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) + if (overlap & 1 << i) + radix_tree_tag_set(&dma_active_cacheline, cln, i); + else + radix_tree_tag_clear(&dma_active_cacheline, cln, i); + + return overlap; +} + +static void active_cacheline_inc_overlap(phys_addr_t cln) +{ + int overlap = active_cacheline_read_overlap(cln); + + overlap = active_cacheline_set_overlap(cln, ++overlap); + + /* If we overflowed the overlap counter then we're potentially + * leaking dma-mappings. Otherwise, if maps and unmaps are + * balanced then this overflow may cause false negatives in + * debug_dma_assert_idle() as the cacheline may be marked idle + * prematurely. + */ + WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP, + "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n", + ACTIVE_CACHELINE_MAX_OVERLAP, &cln); +} + +static int active_cacheline_dec_overlap(phys_addr_t cln) +{ + int overlap = active_cacheline_read_overlap(cln); + + return active_cacheline_set_overlap(cln, --overlap); +} + +static int active_cacheline_insert(struct dma_debug_entry *entry) +{ + phys_addr_t cln = to_cacheline_number(entry); + unsigned long flags; + int rc; + + /* If the device is not writing memory then we don't have any + * concerns about the cpu consuming stale data. This mitigates + * legitimate usages of overlapping mappings. + */ + if (entry->direction == DMA_TO_DEVICE) + return 0; + + spin_lock_irqsave(&radix_lock, flags); + rc = radix_tree_insert(&dma_active_cacheline, cln, entry); + if (rc == -EEXIST) + active_cacheline_inc_overlap(cln); + spin_unlock_irqrestore(&radix_lock, flags); + + return rc; +} + +static void active_cacheline_remove(struct dma_debug_entry *entry) +{ + phys_addr_t cln = to_cacheline_number(entry); + unsigned long flags; + + /* ...mirror the insert case */ + if (entry->direction == DMA_TO_DEVICE) + return; + + spin_lock_irqsave(&radix_lock, flags); + /* since we are counting overlaps the final put of the + * cacheline will occur when the overlap count is 0. + * active_cacheline_dec_overlap() returns -1 in that case + */ + if (active_cacheline_dec_overlap(cln) < 0) + radix_tree_delete(&dma_active_cacheline, cln); + spin_unlock_irqrestore(&radix_lock, flags); +} + +/** + * debug_dma_assert_idle() - assert that a page is not undergoing dma + * @page: page to lookup in the dma_active_cacheline tree + * + * Place a call to this routine in cases where the cpu touching the page + * before the dma completes (page is dma_unmapped) will lead to data + * corruption. + */ +void debug_dma_assert_idle(struct page *page) +{ + static struct dma_debug_entry *ents[CACHELINES_PER_PAGE]; + struct dma_debug_entry *entry = NULL; + void **results = (void **) &ents; + unsigned int nents, i; + unsigned long flags; + phys_addr_t cln; + + if (dma_debug_disabled()) + return; + + if (!page) + return; + + cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT; + spin_lock_irqsave(&radix_lock, flags); + nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln, + CACHELINES_PER_PAGE); + for (i = 0; i < nents; i++) { + phys_addr_t ent_cln = to_cacheline_number(ents[i]); + + if (ent_cln == cln) { + entry = ents[i]; + break; + } else if (ent_cln >= cln + CACHELINES_PER_PAGE) + break; + } + spin_unlock_irqrestore(&radix_lock, flags); + + if (!entry) + return; + + cln = to_cacheline_number(entry); + err_printk(entry->dev, entry, + "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n", + &cln); +} + +/* + * Wrapper function for adding an entry to the hash. + * This function takes care of locking itself. + */ +static void add_dma_entry(struct dma_debug_entry *entry) +{ + struct hash_bucket *bucket; + unsigned long flags; + int rc; + + bucket = get_hash_bucket(entry, &flags); + hash_bucket_add(bucket, entry); + put_hash_bucket(bucket, &flags); + + rc = active_cacheline_insert(entry); + if (rc == -ENOMEM) { + pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n"); + global_disable = true; + } + + /* TODO: report -EEXIST errors here as overlapping mappings are + * not supported by the DMA API + */ +} + +static struct dma_debug_entry *__dma_entry_alloc(void) +{ + struct dma_debug_entry *entry; + + entry = list_entry(free_entries.next, struct dma_debug_entry, list); + list_del(&entry->list); + memset(entry, 0, sizeof(*entry)); + + num_free_entries -= 1; + if (num_free_entries < min_free_entries) + min_free_entries = num_free_entries; + + return entry; +} + +/* struct dma_entry allocator + * + * The next two functions implement the allocator for + * struct dma_debug_entries. + */ +static struct dma_debug_entry *dma_entry_alloc(void) +{ + struct dma_debug_entry *entry; + unsigned long flags; + + spin_lock_irqsave(&free_entries_lock, flags); + + if (list_empty(&free_entries)) { + global_disable = true; + spin_unlock_irqrestore(&free_entries_lock, flags); + pr_err("DMA-API: debugging out of memory - disabling\n"); + return NULL; + } + + entry = __dma_entry_alloc(); + + spin_unlock_irqrestore(&free_entries_lock, flags); + +#ifdef CONFIG_STACKTRACE + entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES; + entry->stacktrace.entries = entry->st_entries; + entry->stacktrace.skip = 2; + save_stack_trace(&entry->stacktrace); +#endif + + return entry; +} + +static void dma_entry_free(struct dma_debug_entry *entry) +{ + unsigned long flags; + + active_cacheline_remove(entry); + + /* + * add to beginning of the list - this way the entries are + * more likely cache hot when they are reallocated. + */ + spin_lock_irqsave(&free_entries_lock, flags); + list_add(&entry->list, &free_entries); + num_free_entries += 1; + spin_unlock_irqrestore(&free_entries_lock, flags); +} + +int dma_debug_resize_entries(u32 num_entries) +{ + int i, delta, ret = 0; + unsigned long flags; + struct dma_debug_entry *entry; + LIST_HEAD(tmp); + + spin_lock_irqsave(&free_entries_lock, flags); + + if (nr_total_entries < num_entries) { + delta = num_entries - nr_total_entries; + + spin_unlock_irqrestore(&free_entries_lock, flags); + + for (i = 0; i < delta; i++) { + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + break; + + list_add_tail(&entry->list, &tmp); + } + + spin_lock_irqsave(&free_entries_lock, flags); + + list_splice(&tmp, &free_entries); + nr_total_entries += i; + num_free_entries += i; + } else { + delta = nr_total_entries - num_entries; + + for (i = 0; i < delta && !list_empty(&free_entries); i++) { + entry = __dma_entry_alloc(); + kfree(entry); + } + + nr_total_entries -= i; + } + + if (nr_total_entries != num_entries) + ret = 1; + + spin_unlock_irqrestore(&free_entries_lock, flags); + + return ret; +} + +/* + * DMA-API debugging init code + * + * The init code does two things: + * 1. Initialize core data structures + * 2. Preallocate a given number of dma_debug_entry structs + */ + +static int prealloc_memory(u32 num_entries) +{ + struct dma_debug_entry *entry, *next_entry; + int i; + + for (i = 0; i < num_entries; ++i) { + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + goto out_err; + + list_add_tail(&entry->list, &free_entries); + } + + num_free_entries = num_entries; + min_free_entries = num_entries; + + pr_info("DMA-API: preallocated %d debug entries\n", num_entries); + + return 0; + +out_err: + + list_for_each_entry_safe(entry, next_entry, &free_entries, list) { + list_del(&entry->list); + kfree(entry); + } + + return -ENOMEM; +} + +static ssize_t filter_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + char buf[NAME_MAX_LEN + 1]; + unsigned long flags; + int len; + + if (!current_driver_name[0]) + return 0; + + /* + * We can't copy to userspace directly because current_driver_name can + * only be read under the driver_name_lock with irqs disabled. So + * create a temporary copy first. + */ + read_lock_irqsave(&driver_name_lock, flags); + len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name); + read_unlock_irqrestore(&driver_name_lock, flags); + + return simple_read_from_buffer(user_buf, count, ppos, buf, len); +} + +static ssize_t filter_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + char buf[NAME_MAX_LEN]; + unsigned long flags; + size_t len; + int i; + + /* + * We can't copy from userspace directly. Access to + * current_driver_name is protected with a write_lock with irqs + * disabled. Since copy_from_user can fault and may sleep we + * need to copy to temporary buffer first + */ + len = min(count, (size_t)(NAME_MAX_LEN - 1)); + if (copy_from_user(buf, userbuf, len)) + return -EFAULT; + + buf[len] = 0; + + write_lock_irqsave(&driver_name_lock, flags); + + /* + * Now handle the string we got from userspace very carefully. + * The rules are: + * - only use the first token we got + * - token delimiter is everything looking like a space + * character (' ', '\n', '\t' ...) + * + */ + if (!isalnum(buf[0])) { + /* + * If the first character userspace gave us is not + * alphanumerical then assume the filter should be + * switched off. + */ + if (current_driver_name[0]) + pr_info("DMA-API: switching off dma-debug driver filter\n"); + current_driver_name[0] = 0; + current_driver = NULL; + goto out_unlock; + } + + /* + * Now parse out the first token and use it as the name for the + * driver to filter for. + */ + for (i = 0; i < NAME_MAX_LEN - 1; ++i) { + current_driver_name[i] = buf[i]; + if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0) + break; + } + current_driver_name[i] = 0; + current_driver = NULL; + + pr_info("DMA-API: enable driver filter for driver [%s]\n", + current_driver_name); + +out_unlock: + write_unlock_irqrestore(&driver_name_lock, flags); + + return count; +} + +static const struct file_operations filter_fops = { + .read = filter_read, + .write = filter_write, + .llseek = default_llseek, +}; + +static int dma_debug_fs_init(void) +{ + dma_debug_dent = debugfs_create_dir("dma-api", NULL); + if (!dma_debug_dent) { + pr_err("DMA-API: can not create debugfs directory\n"); + return -ENOMEM; + } + + global_disable_dent = debugfs_create_bool("disabled", 0444, + dma_debug_dent, + &global_disable); + if (!global_disable_dent) + goto out_err; + + error_count_dent = debugfs_create_u32("error_count", 0444, + dma_debug_dent, &error_count); + if (!error_count_dent) + goto out_err; + + show_all_errors_dent = debugfs_create_u32("all_errors", 0644, + dma_debug_dent, + &show_all_errors); + if (!show_all_errors_dent) + goto out_err; + + show_num_errors_dent = debugfs_create_u32("num_errors", 0644, + dma_debug_dent, + &show_num_errors); + if (!show_num_errors_dent) + goto out_err; + + num_free_entries_dent = debugfs_create_u32("num_free_entries", 0444, + dma_debug_dent, + &num_free_entries); + if (!num_free_entries_dent) + goto out_err; + + min_free_entries_dent = debugfs_create_u32("min_free_entries", 0444, + dma_debug_dent, + &min_free_entries); + if (!min_free_entries_dent) + goto out_err; + + filter_dent = debugfs_create_file("driver_filter", 0644, + dma_debug_dent, NULL, &filter_fops); + if (!filter_dent) + goto out_err; + + return 0; + +out_err: + debugfs_remove_recursive(dma_debug_dent); + + return -ENOMEM; +} + +static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry) +{ + struct dma_debug_entry *entry; + unsigned long flags; + int count = 0, i; + + for (i = 0; i < HASH_SIZE; ++i) { + spin_lock_irqsave(&dma_entry_hash[i].lock, flags); + list_for_each_entry(entry, &dma_entry_hash[i].list, list) { + if (entry->dev == dev) { + count += 1; + *out_entry = entry; + } + } + spin_unlock_irqrestore(&dma_entry_hash[i].lock, flags); + } + + return count; +} + +static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data) +{ + struct device *dev = data; + struct dma_debug_entry *uninitialized_var(entry); + int count; + + if (dma_debug_disabled()) + return 0; + + switch (action) { + case BUS_NOTIFY_UNBOUND_DRIVER: + count = device_dma_allocations(dev, &entry); + if (count == 0) + break; + err_printk(dev, entry, "DMA-API: device driver has pending " + "DMA allocations while released from device " + "[count=%d]\n" + "One of leaked entries details: " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [mapped as %s]\n", + count, entry->dev_addr, entry->size, + dir2name[entry->direction], type2name[entry->type]); + break; + default: + break; + } + + return 0; +} + +void dma_debug_add_bus(struct bus_type *bus) +{ + struct notifier_block *nb; + + if (dma_debug_disabled()) + return; + + nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL); + if (nb == NULL) { + pr_err("dma_debug_add_bus: out of memory\n"); + return; + } + + nb->notifier_call = dma_debug_device_change; + + bus_register_notifier(bus, nb); +} + +static int dma_debug_init(void) +{ + int i; + + /* Do not use dma_debug_initialized here, since we really want to be + * called to set dma_debug_initialized + */ + if (global_disable) + return 0; + + for (i = 0; i < HASH_SIZE; ++i) { + INIT_LIST_HEAD(&dma_entry_hash[i].list); + spin_lock_init(&dma_entry_hash[i].lock); + } + + if (dma_debug_fs_init() != 0) { + pr_err("DMA-API: error creating debugfs entries - disabling\n"); + global_disable = true; + + return 0; + } + + if (prealloc_memory(nr_prealloc_entries) != 0) { + pr_err("DMA-API: debugging out of memory error - disabled\n"); + global_disable = true; + + return 0; + } + + nr_total_entries = num_free_entries; + + dma_debug_initialized = true; + + pr_info("DMA-API: debugging enabled by kernel config\n"); + return 0; +} +core_initcall(dma_debug_init); + +static __init int dma_debug_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (strncmp(str, "off", 3) == 0) { + pr_info("DMA-API: debugging disabled on kernel command line\n"); + global_disable = true; + } + + return 0; +} + +static __init int dma_debug_entries_cmdline(char *str) +{ + if (!str) + return -EINVAL; + if (!get_option(&str, &nr_prealloc_entries)) + nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES; + return 0; +} + +__setup("dma_debug=", dma_debug_cmdline); +__setup("dma_debug_entries=", dma_debug_entries_cmdline); + +static void check_unmap(struct dma_debug_entry *ref) +{ + struct dma_debug_entry *entry; + struct hash_bucket *bucket; + unsigned long flags; + + bucket = get_hash_bucket(ref, &flags); + entry = bucket_find_exact(bucket, ref); + + if (!entry) { + /* must drop lock before calling dma_mapping_error */ + put_hash_bucket(bucket, &flags); + + if (dma_mapping_error(ref->dev, ref->dev_addr)) { + err_printk(ref->dev, NULL, + "DMA-API: device driver tries to free an " + "invalid DMA memory address\n"); + } else { + err_printk(ref->dev, NULL, + "DMA-API: device driver tries to free DMA " + "memory it has not allocated [device " + "address=0x%016llx] [size=%llu bytes]\n", + ref->dev_addr, ref->size); + } + return; + } + + if (ref->size != entry->size) { + err_printk(ref->dev, entry, "DMA-API: device driver frees " + "DMA memory with different size " + "[device address=0x%016llx] [map size=%llu bytes] " + "[unmap size=%llu bytes]\n", + ref->dev_addr, entry->size, ref->size); + } + + if (ref->type != entry->type) { + err_printk(ref->dev, entry, "DMA-API: device driver frees " + "DMA memory with wrong function " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped as %s] [unmapped as %s]\n", + ref->dev_addr, ref->size, + type2name[entry->type], type2name[ref->type]); + } else if ((entry->type == dma_debug_coherent) && + (phys_addr(ref) != phys_addr(entry))) { + err_printk(ref->dev, entry, "DMA-API: device driver frees " + "DMA memory with different CPU address " + "[device address=0x%016llx] [size=%llu bytes] " + "[cpu alloc address=0x%016llx] " + "[cpu free address=0x%016llx]", + ref->dev_addr, ref->size, + phys_addr(entry), + phys_addr(ref)); + } + + if (ref->sg_call_ents && ref->type == dma_debug_sg && + ref->sg_call_ents != entry->sg_call_ents) { + err_printk(ref->dev, entry, "DMA-API: device driver frees " + "DMA sg list with different entry count " + "[map count=%d] [unmap count=%d]\n", + entry->sg_call_ents, ref->sg_call_ents); + } + + /* + * This may be no bug in reality - but most implementations of the + * DMA API don't handle this properly, so check for it here + */ + if (ref->direction != entry->direction) { + err_printk(ref->dev, entry, "DMA-API: device driver frees " + "DMA memory with different direction " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [unmapped with %s]\n", + ref->dev_addr, ref->size, + dir2name[entry->direction], + dir2name[ref->direction]); + } + + /* + * Drivers should use dma_mapping_error() to check the returned + * addresses of dma_map_single() and dma_map_page(). + * If not, print this warning message. See Documentation/DMA-API.txt. + */ + if (entry->map_err_type == MAP_ERR_NOT_CHECKED) { + err_printk(ref->dev, entry, + "DMA-API: device driver failed to check map error" + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped as %s]", + ref->dev_addr, ref->size, + type2name[entry->type]); + } + + hash_bucket_del(entry); + dma_entry_free(entry); + + put_hash_bucket(bucket, &flags); +} + +static void check_for_stack(struct device *dev, + struct page *page, size_t offset) +{ + void *addr; + struct vm_struct *stack_vm_area = task_stack_vm_area(current); + + if (!stack_vm_area) { + /* Stack is direct-mapped. */ + if (PageHighMem(page)) + return; + addr = page_address(page) + offset; + if (object_is_on_stack(addr)) + err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr); + } else { + /* Stack is vmalloced. */ + int i; + + for (i = 0; i < stack_vm_area->nr_pages; i++) { + if (page != stack_vm_area->pages[i]) + continue; + + addr = (u8 *)current->stack + i * PAGE_SIZE + offset; + err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr); + break; + } + } +} + +static inline bool overlap(void *addr, unsigned long len, void *start, void *end) +{ + unsigned long a1 = (unsigned long)addr; + unsigned long b1 = a1 + len; + unsigned long a2 = (unsigned long)start; + unsigned long b2 = (unsigned long)end; + + return !(b1 <= a2 || a1 >= b2); +} + +static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len) +{ + if (overlap(addr, len, _stext, _etext) || + overlap(addr, len, __start_rodata, __end_rodata)) + err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); +} + +static void check_sync(struct device *dev, + struct dma_debug_entry *ref, + bool to_cpu) +{ + struct dma_debug_entry *entry; + struct hash_bucket *bucket; + unsigned long flags; + + bucket = get_hash_bucket(ref, &flags); + + entry = bucket_find_contain(&bucket, ref, &flags); + + if (!entry) { + err_printk(dev, NULL, "DMA-API: device driver tries " + "to sync DMA memory it has not allocated " + "[device address=0x%016llx] [size=%llu bytes]\n", + (unsigned long long)ref->dev_addr, ref->size); + goto out; + } + + if (ref->size > entry->size) { + err_printk(dev, entry, "DMA-API: device driver syncs" + " DMA memory outside allocated range " + "[device address=0x%016llx] " + "[allocation size=%llu bytes] " + "[sync offset+size=%llu]\n", + entry->dev_addr, entry->size, + ref->size); + } + + if (entry->direction == DMA_BIDIRECTIONAL) + goto out; + + if (ref->direction != entry->direction) { + err_printk(dev, entry, "DMA-API: device driver syncs " + "DMA memory with different direction " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [synced with %s]\n", + (unsigned long long)ref->dev_addr, entry->size, + dir2name[entry->direction], + dir2name[ref->direction]); + } + + if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) && + !(ref->direction == DMA_TO_DEVICE)) + err_printk(dev, entry, "DMA-API: device driver syncs " + "device read-only DMA memory for cpu " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [synced with %s]\n", + (unsigned long long)ref->dev_addr, entry->size, + dir2name[entry->direction], + dir2name[ref->direction]); + + if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) && + !(ref->direction == DMA_FROM_DEVICE)) + err_printk(dev, entry, "DMA-API: device driver syncs " + "device write-only DMA memory to device " + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped with %s] [synced with %s]\n", + (unsigned long long)ref->dev_addr, entry->size, + dir2name[entry->direction], + dir2name[ref->direction]); + + if (ref->sg_call_ents && ref->type == dma_debug_sg && + ref->sg_call_ents != entry->sg_call_ents) { + err_printk(ref->dev, entry, "DMA-API: device driver syncs " + "DMA sg list with different entry count " + "[map count=%d] [sync count=%d]\n", + entry->sg_call_ents, ref->sg_call_ents); + } + +out: + put_hash_bucket(bucket, &flags); +} + +static void check_sg_segment(struct device *dev, struct scatterlist *sg) +{ +#ifdef CONFIG_DMA_API_DEBUG_SG + unsigned int max_seg = dma_get_max_seg_size(dev); + u64 start, end, boundary = dma_get_seg_boundary(dev); + + /* + * Either the driver forgot to set dma_parms appropriately, or + * whoever generated the list forgot to check them. + */ + if (sg->length > max_seg) + err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n", + sg->length, max_seg); + /* + * In some cases this could potentially be the DMA API + * implementation's fault, but it would usually imply that + * the scatterlist was built inappropriately to begin with. + */ + start = sg_dma_address(sg); + end = start + sg_dma_len(sg) - 1; + if ((start ^ end) & ~boundary) + err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n", + start, end, boundary); +#endif +} + +void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, + size_t size, int direction, dma_addr_t dma_addr, + bool map_single) +{ + struct dma_debug_entry *entry; + + if (unlikely(dma_debug_disabled())) + return; + + if (dma_mapping_error(dev, dma_addr)) + return; + + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->dev = dev; + entry->type = dma_debug_page; + entry->pfn = page_to_pfn(page); + entry->offset = offset, + entry->dev_addr = dma_addr; + entry->size = size; + entry->direction = direction; + entry->map_err_type = MAP_ERR_NOT_CHECKED; + + if (map_single) + entry->type = dma_debug_single; + + check_for_stack(dev, page, offset); + + if (!PageHighMem(page)) { + void *addr = page_address(page) + offset; + + check_for_illegal_area(dev, addr, size); + } + + add_dma_entry(entry); +} +EXPORT_SYMBOL(debug_dma_map_page); + +void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + struct dma_debug_entry ref; + struct dma_debug_entry *entry; + struct hash_bucket *bucket; + unsigned long flags; + + if (unlikely(dma_debug_disabled())) + return; + + ref.dev = dev; + ref.dev_addr = dma_addr; + bucket = get_hash_bucket(&ref, &flags); + + list_for_each_entry(entry, &bucket->list, list) { + if (!exact_match(&ref, entry)) + continue; + + /* + * The same physical address can be mapped multiple + * times. Without a hardware IOMMU this results in the + * same device addresses being put into the dma-debug + * hash multiple times too. This can result in false + * positives being reported. Therefore we implement a + * best-fit algorithm here which updates the first entry + * from the hash which fits the reference value and is + * not currently listed as being checked. + */ + if (entry->map_err_type == MAP_ERR_NOT_CHECKED) { + entry->map_err_type = MAP_ERR_CHECKED; + break; + } + } + + put_hash_bucket(bucket, &flags); +} +EXPORT_SYMBOL(debug_dma_mapping_error); + +void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, int direction, bool map_single) +{ + struct dma_debug_entry ref = { + .type = dma_debug_page, + .dev = dev, + .dev_addr = addr, + .size = size, + .direction = direction, + }; + + if (unlikely(dma_debug_disabled())) + return; + + if (map_single) + ref.type = dma_debug_single; + + check_unmap(&ref); +} +EXPORT_SYMBOL(debug_dma_unmap_page); + +void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, + int nents, int mapped_ents, int direction) +{ + struct dma_debug_entry *entry; + struct scatterlist *s; + int i; + + if (unlikely(dma_debug_disabled())) + return; + + for_each_sg(sg, s, mapped_ents, i) { + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->type = dma_debug_sg; + entry->dev = dev; + entry->pfn = page_to_pfn(sg_page(s)); + entry->offset = s->offset, + entry->size = sg_dma_len(s); + entry->dev_addr = sg_dma_address(s); + entry->direction = direction; + entry->sg_call_ents = nents; + entry->sg_mapped_ents = mapped_ents; + + check_for_stack(dev, sg_page(s), s->offset); + + if (!PageHighMem(sg_page(s))) { + check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s)); + } + + check_sg_segment(dev, s); + + add_dma_entry(entry); + } +} +EXPORT_SYMBOL(debug_dma_map_sg); + +static int get_nr_mapped_entries(struct device *dev, + struct dma_debug_entry *ref) +{ + struct dma_debug_entry *entry; + struct hash_bucket *bucket; + unsigned long flags; + int mapped_ents; + + bucket = get_hash_bucket(ref, &flags); + entry = bucket_find_exact(bucket, ref); + mapped_ents = 0; + + if (entry) + mapped_ents = entry->sg_mapped_ents; + put_hash_bucket(bucket, &flags); + + return mapped_ents; +} + +void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems, int dir) +{ + struct scatterlist *s; + int mapped_ents = 0, i; + + if (unlikely(dma_debug_disabled())) + return; + + for_each_sg(sglist, s, nelems, i) { + + struct dma_debug_entry ref = { + .type = dma_debug_sg, + .dev = dev, + .pfn = page_to_pfn(sg_page(s)), + .offset = s->offset, + .dev_addr = sg_dma_address(s), + .size = sg_dma_len(s), + .direction = dir, + .sg_call_ents = nelems, + }; + + if (mapped_ents && i >= mapped_ents) + break; + + if (!i) + mapped_ents = get_nr_mapped_entries(dev, &ref); + + check_unmap(&ref); + } +} +EXPORT_SYMBOL(debug_dma_unmap_sg); + +void debug_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t dma_addr, void *virt) +{ + struct dma_debug_entry *entry; + + if (unlikely(dma_debug_disabled())) + return; + + if (unlikely(virt == NULL)) + return; + + /* handle vmalloc and linear addresses */ + if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt)) + return; + + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->type = dma_debug_coherent; + entry->dev = dev; + entry->offset = offset_in_page(virt); + entry->size = size; + entry->dev_addr = dma_addr; + entry->direction = DMA_BIDIRECTIONAL; + + if (is_vmalloc_addr(virt)) + entry->pfn = vmalloc_to_pfn(virt); + else + entry->pfn = page_to_pfn(virt_to_page(virt)); + + add_dma_entry(entry); +} +EXPORT_SYMBOL(debug_dma_alloc_coherent); + +void debug_dma_free_coherent(struct device *dev, size_t size, + void *virt, dma_addr_t addr) +{ + struct dma_debug_entry ref = { + .type = dma_debug_coherent, + .dev = dev, + .offset = offset_in_page(virt), + .dev_addr = addr, + .size = size, + .direction = DMA_BIDIRECTIONAL, + }; + + /* handle vmalloc and linear addresses */ + if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt)) + return; + + if (is_vmalloc_addr(virt)) + ref.pfn = vmalloc_to_pfn(virt); + else + ref.pfn = page_to_pfn(virt_to_page(virt)); + + if (unlikely(dma_debug_disabled())) + return; + + check_unmap(&ref); +} +EXPORT_SYMBOL(debug_dma_free_coherent); + +void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size, + int direction, dma_addr_t dma_addr) +{ + struct dma_debug_entry *entry; + + if (unlikely(dma_debug_disabled())) + return; + + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->type = dma_debug_resource; + entry->dev = dev; + entry->pfn = PHYS_PFN(addr); + entry->offset = offset_in_page(addr); + entry->size = size; + entry->dev_addr = dma_addr; + entry->direction = direction; + entry->map_err_type = MAP_ERR_NOT_CHECKED; + + add_dma_entry(entry); +} +EXPORT_SYMBOL(debug_dma_map_resource); + +void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr, + size_t size, int direction) +{ + struct dma_debug_entry ref = { + .type = dma_debug_resource, + .dev = dev, + .dev_addr = dma_addr, + .size = size, + .direction = direction, + }; + + if (unlikely(dma_debug_disabled())) + return; + + check_unmap(&ref); +} +EXPORT_SYMBOL(debug_dma_unmap_resource); + +void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, + size_t size, int direction) +{ + struct dma_debug_entry ref; + + if (unlikely(dma_debug_disabled())) + return; + + ref.type = dma_debug_single; + ref.dev = dev; + ref.dev_addr = dma_handle; + ref.size = size; + ref.direction = direction; + ref.sg_call_ents = 0; + + check_sync(dev, &ref, true); +} +EXPORT_SYMBOL(debug_dma_sync_single_for_cpu); + +void debug_dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, size_t size, + int direction) +{ + struct dma_debug_entry ref; + + if (unlikely(dma_debug_disabled())) + return; + + ref.type = dma_debug_single; + ref.dev = dev; + ref.dev_addr = dma_handle; + ref.size = size; + ref.direction = direction; + ref.sg_call_ents = 0; + + check_sync(dev, &ref, false); +} +EXPORT_SYMBOL(debug_dma_sync_single_for_device); + +void debug_dma_sync_single_range_for_cpu(struct device *dev, + dma_addr_t dma_handle, + unsigned long offset, size_t size, + int direction) +{ + struct dma_debug_entry ref; + + if (unlikely(dma_debug_disabled())) + return; + + ref.type = dma_debug_single; + ref.dev = dev; + ref.dev_addr = dma_handle; + ref.size = offset + size; + ref.direction = direction; + ref.sg_call_ents = 0; + + check_sync(dev, &ref, true); +} +EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu); + +void debug_dma_sync_single_range_for_device(struct device *dev, + dma_addr_t dma_handle, + unsigned long offset, + size_t size, int direction) +{ + struct dma_debug_entry ref; + + if (unlikely(dma_debug_disabled())) + return; + + ref.type = dma_debug_single; + ref.dev = dev; + ref.dev_addr = dma_handle; + ref.size = offset + size; + ref.direction = direction; + ref.sg_call_ents = 0; + + check_sync(dev, &ref, false); +} +EXPORT_SYMBOL(debug_dma_sync_single_range_for_device); + +void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nelems, int direction) +{ + struct scatterlist *s; + int mapped_ents = 0, i; + + if (unlikely(dma_debug_disabled())) + return; + + for_each_sg(sg, s, nelems, i) { + + struct dma_debug_entry ref = { + .type = dma_debug_sg, + .dev = dev, + .pfn = page_to_pfn(sg_page(s)), + .offset = s->offset, + .dev_addr = sg_dma_address(s), + .size = sg_dma_len(s), + .direction = direction, + .sg_call_ents = nelems, + }; + + if (!i) + mapped_ents = get_nr_mapped_entries(dev, &ref); + + if (i >= mapped_ents) + break; + + check_sync(dev, &ref, true); + } +} +EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu); + +void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nelems, int direction) +{ + struct scatterlist *s; + int mapped_ents = 0, i; + + if (unlikely(dma_debug_disabled())) + return; + + for_each_sg(sg, s, nelems, i) { + + struct dma_debug_entry ref = { + .type = dma_debug_sg, + .dev = dev, + .pfn = page_to_pfn(sg_page(s)), + .offset = s->offset, + .dev_addr = sg_dma_address(s), + .size = sg_dma_len(s), + .direction = direction, + .sg_call_ents = nelems, + }; + if (!i) + mapped_ents = get_nr_mapped_entries(dev, &ref); + + if (i >= mapped_ents) + break; + + check_sync(dev, &ref, false); + } +} +EXPORT_SYMBOL(debug_dma_sync_sg_for_device); + +static int __init dma_debug_driver_setup(char *str) +{ + int i; + + for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) { + current_driver_name[i] = *str; + if (*str == 0) + break; + } + + if (current_driver_name[0]) + pr_info("DMA-API: enable driver filter for driver [%s]\n", + current_driver_name); + + + return 1; +} +__setup("dma_debug_driver=", dma_debug_driver_setup); diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c new file mode 100644 index 000000000000..c2860c5a9e96 --- /dev/null +++ b/kernel/dma/direct.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DMA operations that map physical memory directly without using an IOMMU or + * flushing caches. + */ +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/dma-direct.h> +#include <linux/scatterlist.h> +#include <linux/dma-contiguous.h> +#include <linux/pfn.h> +#include <linux/set_memory.h> + +#define DIRECT_MAPPING_ERROR 0 + +/* + * Most architectures use ZONE_DMA for the first 16 Megabytes, but + * some use it for entirely different regions: + */ +#ifndef ARCH_ZONE_DMA_BITS +#define ARCH_ZONE_DMA_BITS 24 +#endif + +/* + * For AMD SEV all DMA must be to unencrypted addresses. + */ +static inline bool force_dma_unencrypted(void) +{ + return sev_active(); +} + +static bool +check_addr(struct device *dev, dma_addr_t dma_addr, size_t size, + const char *caller) +{ + if (unlikely(dev && !dma_capable(dev, dma_addr, size))) { + if (!dev->dma_mask) { + dev_err(dev, + "%s: call on device without dma_mask\n", + caller); + return false; + } + + if (*dev->dma_mask >= DMA_BIT_MASK(32)) { + dev_err(dev, + "%s: overflow %pad+%zu of device mask %llx\n", + caller, &dma_addr, size, *dev->dma_mask); + } + return false; + } + return true; +} + +static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) +{ + dma_addr_t addr = force_dma_unencrypted() ? + __phys_to_dma(dev, phys) : phys_to_dma(dev, phys); + return addr + size - 1 <= dev->coherent_dma_mask; +} + +void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + int page_order = get_order(size); + struct page *page = NULL; + void *ret; + + /* we always manually zero the memory once we are done: */ + gfp &= ~__GFP_ZERO; + + /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */ + if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + gfp |= GFP_DMA; + if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) + gfp |= GFP_DMA32; + +again: + /* CMA can be used only in the context which permits sleeping */ + if (gfpflags_allow_blocking(gfp)) { + page = dma_alloc_from_contiguous(dev, count, page_order, gfp); + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } + } + if (!page) + page = alloc_pages_node(dev_to_node(dev), gfp, page_order); + + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + __free_pages(page, page_order); + page = NULL; + + if (IS_ENABLED(CONFIG_ZONE_DMA32) && + dev->coherent_dma_mask < DMA_BIT_MASK(64) && + !(gfp & (GFP_DMA32 | GFP_DMA))) { + gfp |= GFP_DMA32; + goto again; + } + + if (IS_ENABLED(CONFIG_ZONE_DMA) && + dev->coherent_dma_mask < DMA_BIT_MASK(32) && + !(gfp & GFP_DMA)) { + gfp = (gfp & ~GFP_DMA32) | GFP_DMA; + goto again; + } + } + + if (!page) + return NULL; + ret = page_address(page); + if (force_dma_unencrypted()) { + set_memory_decrypted((unsigned long)ret, 1 << page_order); + *dma_handle = __phys_to_dma(dev, page_to_phys(page)); + } else { + *dma_handle = phys_to_dma(dev, page_to_phys(page)); + } + memset(ret, 0, size); + return ret; +} + +/* + * NOTE: this function must never look at the dma_addr argument, because we want + * to be able to use it as a helper for iommu implementations as well. + */ +void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_addr, unsigned long attrs) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + unsigned int page_order = get_order(size); + + if (force_dma_unencrypted()) + set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order); + if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count)) + free_pages((unsigned long)cpu_addr, page_order); +} + +dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + dma_addr_t dma_addr = phys_to_dma(dev, page_to_phys(page)) + offset; + + if (!check_addr(dev, dma_addr, size, __func__)) + return DIRECT_MAPPING_ERROR; + return dma_addr; +} + +int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, + enum dma_data_direction dir, unsigned long attrs) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sgl, sg, nents, i) { + BUG_ON(!sg_page(sg)); + + sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg)); + if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__)) + return 0; + sg_dma_len(sg) = sg->length; + } + + return nents; +} + +int dma_direct_supported(struct device *dev, u64 mask) +{ +#ifdef CONFIG_ZONE_DMA + if (mask < DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + return 0; +#else + /* + * Because 32-bit DMA masks are so common we expect every architecture + * to be able to satisfy them - either by not supporting more physical + * memory, or by providing a ZONE_DMA32. If neither is the case, the + * architecture needs to use an IOMMU instead of the direct mapping. + */ + if (mask < DMA_BIT_MASK(32)) + return 0; +#endif + /* + * Upstream PCI/PCIe bridges or SoC interconnects may not carry + * as many DMA address bits as the device itself supports. + */ + if (dev->bus_dma_mask && mask > dev->bus_dma_mask) + return 0; + return 1; +} + +int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr == DIRECT_MAPPING_ERROR; +} + +const struct dma_map_ops dma_direct_ops = { + .alloc = dma_direct_alloc, + .free = dma_direct_free, + .map_page = dma_direct_map_page, + .map_sg = dma_direct_map_sg, + .dma_supported = dma_direct_supported, + .mapping_error = dma_direct_mapping_error, +}; +EXPORT_SYMBOL(dma_direct_ops); diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c new file mode 100644 index 000000000000..d2a92ddaac4d --- /dev/null +++ b/kernel/dma/mapping.c @@ -0,0 +1,345 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * arch-independent dma-mapping routines + * + * Copyright (c) 2006 SUSE Linux Products GmbH + * Copyright (c) 2006 Tejun Heo <teheo@suse.de> + */ + +#include <linux/acpi.h> +#include <linux/dma-mapping.h> +#include <linux/export.h> +#include <linux/gfp.h> +#include <linux/of_device.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +/* + * Managed DMA API + */ +struct dma_devres { + size_t size; + void *vaddr; + dma_addr_t dma_handle; + unsigned long attrs; +}; + +static void dmam_release(struct device *dev, void *res) +{ + struct dma_devres *this = res; + + dma_free_attrs(dev, this->size, this->vaddr, this->dma_handle, + this->attrs); +} + +static int dmam_match(struct device *dev, void *res, void *match_data) +{ + struct dma_devres *this = res, *match = match_data; + + if (this->vaddr == match->vaddr) { + WARN_ON(this->size != match->size || + this->dma_handle != match->dma_handle); + return 1; + } + return 0; +} + +/** + * dmam_alloc_coherent - Managed dma_alloc_coherent() + * @dev: Device to allocate coherent memory for + * @size: Size of allocation + * @dma_handle: Out argument for allocated DMA handle + * @gfp: Allocation flags + * + * Managed dma_alloc_coherent(). Memory allocated using this function + * will be automatically released on driver detach. + * + * RETURNS: + * Pointer to allocated memory on success, NULL on failure. + */ +void *dmam_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp) +{ + struct dma_devres *dr; + void *vaddr; + + dr = devres_alloc(dmam_release, sizeof(*dr), gfp); + if (!dr) + return NULL; + + vaddr = dma_alloc_coherent(dev, size, dma_handle, gfp); + if (!vaddr) { + devres_free(dr); + return NULL; + } + + dr->vaddr = vaddr; + dr->dma_handle = *dma_handle; + dr->size = size; + + devres_add(dev, dr); + + return vaddr; +} +EXPORT_SYMBOL(dmam_alloc_coherent); + +/** + * dmam_free_coherent - Managed dma_free_coherent() + * @dev: Device to free coherent memory for + * @size: Size of allocation + * @vaddr: Virtual address of the memory to free + * @dma_handle: DMA handle of the memory to free + * + * Managed dma_free_coherent(). + */ +void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle) +{ + struct dma_devres match_data = { size, vaddr, dma_handle }; + + dma_free_coherent(dev, size, vaddr, dma_handle); + WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data)); +} +EXPORT_SYMBOL(dmam_free_coherent); + +/** + * dmam_alloc_attrs - Managed dma_alloc_attrs() + * @dev: Device to allocate non_coherent memory for + * @size: Size of allocation + * @dma_handle: Out argument for allocated DMA handle + * @gfp: Allocation flags + * @attrs: Flags in the DMA_ATTR_* namespace. + * + * Managed dma_alloc_attrs(). Memory allocated using this function will be + * automatically released on driver detach. + * + * RETURNS: + * Pointer to allocated memory on success, NULL on failure. + */ +void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + struct dma_devres *dr; + void *vaddr; + + dr = devres_alloc(dmam_release, sizeof(*dr), gfp); + if (!dr) + return NULL; + + vaddr = dma_alloc_attrs(dev, size, dma_handle, gfp, attrs); + if (!vaddr) { + devres_free(dr); + return NULL; + } + + dr->vaddr = vaddr; + dr->dma_handle = *dma_handle; + dr->size = size; + dr->attrs = attrs; + + devres_add(dev, dr); + + return vaddr; +} +EXPORT_SYMBOL(dmam_alloc_attrs); + +#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT + +static void dmam_coherent_decl_release(struct device *dev, void *res) +{ + dma_release_declared_memory(dev); +} + +/** + * dmam_declare_coherent_memory - Managed dma_declare_coherent_memory() + * @dev: Device to declare coherent memory for + * @phys_addr: Physical address of coherent memory to be declared + * @device_addr: Device address of coherent memory to be declared + * @size: Size of coherent memory to be declared + * @flags: Flags + * + * Managed dma_declare_coherent_memory(). + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int dmam_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, + dma_addr_t device_addr, size_t size, int flags) +{ + void *res; + int rc; + + res = devres_alloc(dmam_coherent_decl_release, 0, GFP_KERNEL); + if (!res) + return -ENOMEM; + + rc = dma_declare_coherent_memory(dev, phys_addr, device_addr, size, + flags); + if (!rc) + devres_add(dev, res); + else + devres_free(res); + + return rc; +} +EXPORT_SYMBOL(dmam_declare_coherent_memory); + +/** + * dmam_release_declared_memory - Managed dma_release_declared_memory(). + * @dev: Device to release declared coherent memory for + * + * Managed dmam_release_declared_memory(). + */ +void dmam_release_declared_memory(struct device *dev) +{ + WARN_ON(devres_destroy(dev, dmam_coherent_decl_release, NULL, NULL)); +} +EXPORT_SYMBOL(dmam_release_declared_memory); + +#endif + +/* + * Create scatter-list for the already allocated DMA buffer. + */ +int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t handle, size_t size) +{ + struct page *page = virt_to_page(cpu_addr); + int ret; + + ret = sg_alloc_table(sgt, 1, GFP_KERNEL); + if (unlikely(ret)) + return ret; + + sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); + return 0; +} +EXPORT_SYMBOL(dma_common_get_sgtable); + +/* + * Create userspace mapping for the DMA-coherent memory. + */ +int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size) +{ + int ret = -ENXIO; +#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP + unsigned long user_count = vma_pages(vma); + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + unsigned long off = vma->vm_pgoff; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; + + if (off < count && user_count <= (count - off)) + ret = remap_pfn_range(vma, vma->vm_start, + page_to_pfn(virt_to_page(cpu_addr)) + off, + user_count << PAGE_SHIFT, + vma->vm_page_prot); +#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */ + + return ret; +} +EXPORT_SYMBOL(dma_common_mmap); + +#ifdef CONFIG_MMU +static struct vm_struct *__dma_common_pages_remap(struct page **pages, + size_t size, unsigned long vm_flags, pgprot_t prot, + const void *caller) +{ + struct vm_struct *area; + + area = get_vm_area_caller(size, vm_flags, caller); + if (!area) + return NULL; + + if (map_vm_area(area, prot, pages)) { + vunmap(area->addr); + return NULL; + } + + return area; +} + +/* + * remaps an array of PAGE_SIZE pages into another vm_area + * Cannot be used in non-sleeping contexts + */ +void *dma_common_pages_remap(struct page **pages, size_t size, + unsigned long vm_flags, pgprot_t prot, + const void *caller) +{ + struct vm_struct *area; + + area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller); + if (!area) + return NULL; + + area->pages = pages; + + return area->addr; +} + +/* + * remaps an allocated contiguous region into another vm_area. + * Cannot be used in non-sleeping contexts + */ + +void *dma_common_contiguous_remap(struct page *page, size_t size, + unsigned long vm_flags, + pgprot_t prot, const void *caller) +{ + int i; + struct page **pages; + struct vm_struct *area; + + pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL); + if (!pages) + return NULL; + + for (i = 0; i < (size >> PAGE_SHIFT); i++) + pages[i] = nth_page(page, i); + + area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller); + + kfree(pages); + + if (!area) + return NULL; + return area->addr; +} + +/* + * unmaps a range previously mapped by dma_common_*_remap + */ +void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags) +{ + struct vm_struct *area = find_vm_area(cpu_addr); + + if (!area || (area->flags & vm_flags) != vm_flags) { + WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr); + return; + } + + unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size)); + vunmap(cpu_addr); +} +#endif + +/* + * enables DMA API use for a device + */ +int dma_configure(struct device *dev) +{ + if (dev->bus->dma_configure) + return dev->bus->dma_configure(dev); + return 0; +} + +void dma_deconfigure(struct device *dev) +{ + of_dma_deconfigure(dev); + acpi_dma_deconfigure(dev); +} diff --git a/kernel/dma/noncoherent.c b/kernel/dma/noncoherent.c new file mode 100644 index 000000000000..031fe235d958 --- /dev/null +++ b/kernel/dma/noncoherent.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018 Christoph Hellwig. + * + * DMA operations that map physical memory directly without providing cache + * coherence. + */ +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> +#include <linux/scatterlist.h> + +static void dma_noncoherent_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir); +} + +static void dma_noncoherent_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); +} + +static dma_addr_t dma_noncoherent_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + dma_addr_t addr; + + addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); + if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(dev, page_to_phys(page) + offset, + size, dir); + return addr; +} + +static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs); + if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir); + return nents; +} + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) +static void dma_noncoherent_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir); + arch_sync_dma_for_cpu_all(dev); +} + +static void dma_noncoherent_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); + arch_sync_dma_for_cpu_all(dev); +} + +static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir); +} + +static void dma_noncoherent_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir); +} +#endif + +const struct dma_map_ops dma_noncoherent_ops = { + .alloc = arch_dma_alloc, + .free = arch_dma_free, + .mmap = arch_dma_mmap, + .sync_single_for_device = dma_noncoherent_sync_single_for_device, + .sync_sg_for_device = dma_noncoherent_sync_sg_for_device, + .map_page = dma_noncoherent_map_page, + .map_sg = dma_noncoherent_map_sg, +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) + .sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu, + .sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu, + .unmap_page = dma_noncoherent_unmap_page, + .unmap_sg = dma_noncoherent_unmap_sg, +#endif + .dma_supported = dma_direct_supported, + .mapping_error = dma_direct_mapping_error, + .cache_sync = arch_dma_cache_sync, +}; +EXPORT_SYMBOL(dma_noncoherent_ops); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c new file mode 100644 index 000000000000..4f8a6dbf0b60 --- /dev/null +++ b/kernel/dma/swiotlb.c @@ -0,0 +1,1086 @@ +/* + * Dynamic DMA mapping support. + * + * This implementation is a fallback for platforms that do not support + * I/O TLBs (aka DMA address translation hardware). + * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com> + * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com> + * Copyright (C) 2000, 2003 Hewlett-Packard Co + * David Mosberger-Tang <davidm@hpl.hp.com> + * + * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API. + * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid + * unnecessary i-cache flushing. + * 04/07/.. ak Better overflow handling. Assorted fixes. + * 05/09/10 linville Add support for syncing ranges, support syncing for + * DMA_BIDIRECTIONAL mappings, miscellaneous cleanup. + * 08/12/11 beckyb Add highmem support + */ + +#define pr_fmt(fmt) "software IO TLB: " fmt + +#include <linux/cache.h> +#include <linux/dma-direct.h> +#include <linux/mm.h> +#include <linux/export.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/swiotlb.h> +#include <linux/pfn.h> +#include <linux/types.h> +#include <linux/ctype.h> +#include <linux/highmem.h> +#include <linux/gfp.h> +#include <linux/scatterlist.h> +#include <linux/mem_encrypt.h> +#include <linux/set_memory.h> + +#include <asm/io.h> +#include <asm/dma.h> + +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/iommu-helper.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/swiotlb.h> + +#define OFFSET(val,align) ((unsigned long) \ + ( (val) & ( (align) - 1))) + +#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) + +/* + * Minimum IO TLB size to bother booting with. Systems with mainly + * 64bit capable cards will only lightly use the swiotlb. If we can't + * allocate a contiguous 1MB, we're probably in trouble anyway. + */ +#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT) + +enum swiotlb_force swiotlb_force; + +/* + * Used to do a quick range check in swiotlb_tbl_unmap_single and + * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this + * API. + */ +static phys_addr_t io_tlb_start, io_tlb_end; + +/* + * The number of IO TLB blocks (in groups of 64) between io_tlb_start and + * io_tlb_end. This is command line adjustable via setup_io_tlb_npages. + */ +static unsigned long io_tlb_nslabs; + +/* + * When the IOMMU overflows we return a fallback buffer. This sets the size. + */ +static unsigned long io_tlb_overflow = 32*1024; + +static phys_addr_t io_tlb_overflow_buffer; + +/* + * This is a free list describing the number of free entries available from + * each index + */ +static unsigned int *io_tlb_list; +static unsigned int io_tlb_index; + +/* + * Max segment that we can provide which (if pages are contingous) will + * not be bounced (unless SWIOTLB_FORCE is set). + */ +unsigned int max_segment; + +/* + * We need to save away the original address corresponding to a mapped entry + * for the sync operations. + */ +#define INVALID_PHYS_ADDR (~(phys_addr_t)0) +static phys_addr_t *io_tlb_orig_addr; + +/* + * Protect the above data structures in the map and unmap calls + */ +static DEFINE_SPINLOCK(io_tlb_lock); + +static int late_alloc; + +static int __init +setup_io_tlb_npages(char *str) +{ + if (isdigit(*str)) { + io_tlb_nslabs = simple_strtoul(str, &str, 0); + /* avoid tail segment of size < IO_TLB_SEGSIZE */ + io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + } + if (*str == ',') + ++str; + if (!strcmp(str, "force")) { + swiotlb_force = SWIOTLB_FORCE; + } else if (!strcmp(str, "noforce")) { + swiotlb_force = SWIOTLB_NO_FORCE; + io_tlb_nslabs = 1; + } + + return 0; +} +early_param("swiotlb", setup_io_tlb_npages); +/* make io_tlb_overflow tunable too? */ + +unsigned long swiotlb_nr_tbl(void) +{ + return io_tlb_nslabs; +} +EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); + +unsigned int swiotlb_max_segment(void) +{ + return max_segment; +} +EXPORT_SYMBOL_GPL(swiotlb_max_segment); + +void swiotlb_set_max_segment(unsigned int val) +{ + if (swiotlb_force == SWIOTLB_FORCE) + max_segment = 1; + else + max_segment = rounddown(val, PAGE_SIZE); +} + +/* default to 64MB */ +#define IO_TLB_DEFAULT_SIZE (64UL<<20) +unsigned long swiotlb_size_or_default(void) +{ + unsigned long size; + + size = io_tlb_nslabs << IO_TLB_SHIFT; + + return size ? size : (IO_TLB_DEFAULT_SIZE); +} + +static bool no_iotlb_memory; + +void swiotlb_print_info(void) +{ + unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; + + if (no_iotlb_memory) { + pr_warn("No low mem\n"); + return; + } + + pr_info("mapped [mem %#010llx-%#010llx] (%luMB)\n", + (unsigned long long)io_tlb_start, + (unsigned long long)io_tlb_end, + bytes >> 20); +} + +/* + * Early SWIOTLB allocation may be too early to allow an architecture to + * perform the desired operations. This function allows the architecture to + * call SWIOTLB when the operations are possible. It needs to be called + * before the SWIOTLB memory is used. + */ +void __init swiotlb_update_mem_attributes(void) +{ + void *vaddr; + unsigned long bytes; + + if (no_iotlb_memory || late_alloc) + return; + + vaddr = phys_to_virt(io_tlb_start); + bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT); + set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); + memset(vaddr, 0, bytes); + + vaddr = phys_to_virt(io_tlb_overflow_buffer); + bytes = PAGE_ALIGN(io_tlb_overflow); + set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); + memset(vaddr, 0, bytes); +} + +int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) +{ + void *v_overflow_buffer; + unsigned long i, bytes; + + bytes = nslabs << IO_TLB_SHIFT; + + io_tlb_nslabs = nslabs; + io_tlb_start = __pa(tlb); + io_tlb_end = io_tlb_start + bytes; + + /* + * Get the overflow emergency buffer + */ + v_overflow_buffer = memblock_virt_alloc_low_nopanic( + PAGE_ALIGN(io_tlb_overflow), + PAGE_SIZE); + if (!v_overflow_buffer) + return -ENOMEM; + + io_tlb_overflow_buffer = __pa(v_overflow_buffer); + + /* + * Allocate and initialize the free list array. This array is used + * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE + * between io_tlb_start and io_tlb_end. + */ + io_tlb_list = memblock_virt_alloc( + PAGE_ALIGN(io_tlb_nslabs * sizeof(int)), + PAGE_SIZE); + io_tlb_orig_addr = memblock_virt_alloc( + PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)), + PAGE_SIZE); + for (i = 0; i < io_tlb_nslabs; i++) { + io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); + io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; + } + io_tlb_index = 0; + + if (verbose) + swiotlb_print_info(); + + swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT); + return 0; +} + +/* + * Statically reserve bounce buffer space and initialize bounce buffer data + * structures for the software IO TLB used to implement the DMA API. + */ +void __init +swiotlb_init(int verbose) +{ + size_t default_size = IO_TLB_DEFAULT_SIZE; + unsigned char *vstart; + unsigned long bytes; + + if (!io_tlb_nslabs) { + io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); + io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + } + + bytes = io_tlb_nslabs << IO_TLB_SHIFT; + + /* Get IO TLB memory from the low pages */ + vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); + if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) + return; + + if (io_tlb_start) + memblock_free_early(io_tlb_start, + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + pr_warn("Cannot allocate buffer"); + no_iotlb_memory = true; +} + +/* + * Systems with larger DMA zones (those that don't support ISA) can + * initialize the swiotlb later using the slab allocator if needed. + * This should be just like above, but with some error catching. + */ +int +swiotlb_late_init_with_default_size(size_t default_size) +{ + unsigned long bytes, req_nslabs = io_tlb_nslabs; + unsigned char *vstart = NULL; + unsigned int order; + int rc = 0; + + if (!io_tlb_nslabs) { + io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); + io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + } + + /* + * Get IO TLB memory from the low pages + */ + order = get_order(io_tlb_nslabs << IO_TLB_SHIFT); + io_tlb_nslabs = SLABS_PER_PAGE << order; + bytes = io_tlb_nslabs << IO_TLB_SHIFT; + + while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { + vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, + order); + if (vstart) + break; + order--; + } + + if (!vstart) { + io_tlb_nslabs = req_nslabs; + return -ENOMEM; + } + if (order != get_order(bytes)) { + pr_warn("only able to allocate %ld MB\n", + (PAGE_SIZE << order) >> 20); + io_tlb_nslabs = SLABS_PER_PAGE << order; + } + rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs); + if (rc) + free_pages((unsigned long)vstart, order); + + return rc; +} + +int +swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) +{ + unsigned long i, bytes; + unsigned char *v_overflow_buffer; + + bytes = nslabs << IO_TLB_SHIFT; + + io_tlb_nslabs = nslabs; + io_tlb_start = virt_to_phys(tlb); + io_tlb_end = io_tlb_start + bytes; + + set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); + memset(tlb, 0, bytes); + + /* + * Get the overflow emergency buffer + */ + v_overflow_buffer = (void *)__get_free_pages(GFP_DMA, + get_order(io_tlb_overflow)); + if (!v_overflow_buffer) + goto cleanup2; + + set_memory_decrypted((unsigned long)v_overflow_buffer, + io_tlb_overflow >> PAGE_SHIFT); + memset(v_overflow_buffer, 0, io_tlb_overflow); + io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer); + + /* + * Allocate and initialize the free list array. This array is used + * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE + * between io_tlb_start and io_tlb_end. + */ + io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL, + get_order(io_tlb_nslabs * sizeof(int))); + if (!io_tlb_list) + goto cleanup3; + + io_tlb_orig_addr = (phys_addr_t *) + __get_free_pages(GFP_KERNEL, + get_order(io_tlb_nslabs * + sizeof(phys_addr_t))); + if (!io_tlb_orig_addr) + goto cleanup4; + + for (i = 0; i < io_tlb_nslabs; i++) { + io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); + io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; + } + io_tlb_index = 0; + + swiotlb_print_info(); + + late_alloc = 1; + + swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT); + + return 0; + +cleanup4: + free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * + sizeof(int))); + io_tlb_list = NULL; +cleanup3: + free_pages((unsigned long)v_overflow_buffer, + get_order(io_tlb_overflow)); + io_tlb_overflow_buffer = 0; +cleanup2: + io_tlb_end = 0; + io_tlb_start = 0; + io_tlb_nslabs = 0; + max_segment = 0; + return -ENOMEM; +} + +void __init swiotlb_exit(void) +{ + if (!io_tlb_orig_addr) + return; + + if (late_alloc) { + free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer), + get_order(io_tlb_overflow)); + free_pages((unsigned long)io_tlb_orig_addr, + get_order(io_tlb_nslabs * sizeof(phys_addr_t))); + free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * + sizeof(int))); + free_pages((unsigned long)phys_to_virt(io_tlb_start), + get_order(io_tlb_nslabs << IO_TLB_SHIFT)); + } else { + memblock_free_late(io_tlb_overflow_buffer, + PAGE_ALIGN(io_tlb_overflow)); + memblock_free_late(__pa(io_tlb_orig_addr), + PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); + memblock_free_late(__pa(io_tlb_list), + PAGE_ALIGN(io_tlb_nslabs * sizeof(int))); + memblock_free_late(io_tlb_start, + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + } + io_tlb_nslabs = 0; + max_segment = 0; +} + +int is_swiotlb_buffer(phys_addr_t paddr) +{ + return paddr >= io_tlb_start && paddr < io_tlb_end; +} + +/* + * Bounce: copy the swiotlb buffer back to the original dma location + */ +static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir) +{ + unsigned long pfn = PFN_DOWN(orig_addr); + unsigned char *vaddr = phys_to_virt(tlb_addr); + + if (PageHighMem(pfn_to_page(pfn))) { + /* The buffer does not have a mapping. Map it in and copy */ + unsigned int offset = orig_addr & ~PAGE_MASK; + char *buffer; + unsigned int sz = 0; + unsigned long flags; + + while (size) { + sz = min_t(size_t, PAGE_SIZE - offset, size); + + local_irq_save(flags); + buffer = kmap_atomic(pfn_to_page(pfn)); + if (dir == DMA_TO_DEVICE) + memcpy(vaddr, buffer + offset, sz); + else + memcpy(buffer + offset, vaddr, sz); + kunmap_atomic(buffer); + local_irq_restore(flags); + + size -= sz; + pfn++; + vaddr += sz; + offset = 0; + } + } else if (dir == DMA_TO_DEVICE) { + memcpy(vaddr, phys_to_virt(orig_addr), size); + } else { + memcpy(phys_to_virt(orig_addr), vaddr, size); + } +} + +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, + dma_addr_t tbl_dma_addr, + phys_addr_t orig_addr, size_t size, + enum dma_data_direction dir, + unsigned long attrs) +{ + unsigned long flags; + phys_addr_t tlb_addr; + unsigned int nslots, stride, index, wrap; + int i; + unsigned long mask; + unsigned long offset_slots; + unsigned long max_slots; + + if (no_iotlb_memory) + panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); + + if (mem_encrypt_active()) + pr_warn_once("%s is active and system is using DMA bounce buffers\n", + sme_active() ? "SME" : "SEV"); + + mask = dma_get_seg_boundary(hwdev); + + tbl_dma_addr &= mask; + + offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + + /* + * Carefully handle integer overflow which can occur when mask == ~0UL. + */ + max_slots = mask + 1 + ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT + : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); + + /* + * For mappings greater than or equal to a page, we limit the stride + * (and hence alignment) to a page size. + */ + nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + if (size >= PAGE_SIZE) + stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); + else + stride = 1; + + BUG_ON(!nslots); + + /* + * Find suitable number of IO TLB entries size that will fit this + * request and allocate a buffer from that IO TLB pool. + */ + spin_lock_irqsave(&io_tlb_lock, flags); + index = ALIGN(io_tlb_index, stride); + if (index >= io_tlb_nslabs) + index = 0; + wrap = index; + + do { + while (iommu_is_span_boundary(index, nslots, offset_slots, + max_slots)) { + index += stride; + if (index >= io_tlb_nslabs) + index = 0; + if (index == wrap) + goto not_found; + } + + /* + * If we find a slot that indicates we have 'nslots' number of + * contiguous buffers, we allocate the buffers from that slot + * and mark the entries as '0' indicating unavailable. + */ + if (io_tlb_list[index] >= nslots) { + int count = 0; + + for (i = index; i < (int) (index + nslots); i++) + io_tlb_list[i] = 0; + for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--) + io_tlb_list[i] = ++count; + tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT); + + /* + * Update the indices to avoid searching in the next + * round. + */ + io_tlb_index = ((index + nslots) < io_tlb_nslabs + ? (index + nslots) : 0); + + goto found; + } + index += stride; + if (index >= io_tlb_nslabs) + index = 0; + } while (index != wrap); + +not_found: + spin_unlock_irqrestore(&io_tlb_lock, flags); + if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) + dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size); + return SWIOTLB_MAP_ERROR; +found: + spin_unlock_irqrestore(&io_tlb_lock, flags); + + /* + * Save away the mapping from the original address to the DMA address. + * This is needed when we sync the memory. Then we sync the buffer if + * needed. + */ + for (i = 0; i < nslots; i++) + io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && + (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) + swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE); + + return tlb_addr; +} + +/* + * Allocates bounce buffer and returns its physical address. + */ +static phys_addr_t +map_single(struct device *hwdev, phys_addr_t phys, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + dma_addr_t start_dma_addr; + + if (swiotlb_force == SWIOTLB_NO_FORCE) { + dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n", + &phys); + return SWIOTLB_MAP_ERROR; + } + + start_dma_addr = __phys_to_dma(hwdev, io_tlb_start); + return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, + dir, attrs); +} + +/* + * tlb_addr is the physical address of the bounce buffer to unmap. + */ +void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + unsigned long flags; + int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; + phys_addr_t orig_addr = io_tlb_orig_addr[index]; + + /* + * First, sync the memory before unmapping the entry + */ + if (orig_addr != INVALID_PHYS_ADDR && + !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && + ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) + swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE); + + /* + * Return the buffer to the free list by setting the corresponding + * entries to indicate the number of contiguous entries available. + * While returning the entries to the free list, we merge the entries + * with slots below and above the pool being returned. + */ + spin_lock_irqsave(&io_tlb_lock, flags); + { + count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ? + io_tlb_list[index + nslots] : 0); + /* + * Step 1: return the slots to the free list, merging the + * slots with superceeding slots + */ + for (i = index + nslots - 1; i >= index; i--) { + io_tlb_list[i] = ++count; + io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; + } + /* + * Step 2: merge the returned slots with the preceding slots, + * if available (non zero) + */ + for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--) + io_tlb_list[i] = ++count; + } + spin_unlock_irqrestore(&io_tlb_lock, flags); +} + +void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir, + enum dma_sync_target target) +{ + int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; + phys_addr_t orig_addr = io_tlb_orig_addr[index]; + + if (orig_addr == INVALID_PHYS_ADDR) + return; + orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1); + + switch (target) { + case SYNC_FOR_CPU: + if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) + swiotlb_bounce(orig_addr, tlb_addr, + size, DMA_FROM_DEVICE); + else + BUG_ON(dir != DMA_TO_DEVICE); + break; + case SYNC_FOR_DEVICE: + if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) + swiotlb_bounce(orig_addr, tlb_addr, + size, DMA_TO_DEVICE); + else + BUG_ON(dir != DMA_FROM_DEVICE); + break; + default: + BUG(); + } +} + +static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr, + size_t size) +{ + u64 mask = DMA_BIT_MASK(32); + + if (dev && dev->coherent_dma_mask) + mask = dev->coherent_dma_mask; + return addr + size - 1 <= mask; +} + +static void * +swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, + unsigned long attrs) +{ + phys_addr_t phys_addr; + + if (swiotlb_force == SWIOTLB_NO_FORCE) + goto out_warn; + + phys_addr = swiotlb_tbl_map_single(dev, + __phys_to_dma(dev, io_tlb_start), + 0, size, DMA_FROM_DEVICE, attrs); + if (phys_addr == SWIOTLB_MAP_ERROR) + goto out_warn; + + *dma_handle = __phys_to_dma(dev, phys_addr); + if (!dma_coherent_ok(dev, *dma_handle, size)) + goto out_unmap; + + memset(phys_to_virt(phys_addr), 0, size); + return phys_to_virt(phys_addr); + +out_unmap: + dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n", + (unsigned long long)dev->coherent_dma_mask, + (unsigned long long)*dma_handle); + + /* + * DMA_TO_DEVICE to avoid memcpy in unmap_single. + * DMA_ATTR_SKIP_CPU_SYNC is optional. + */ + swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); +out_warn: + if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) { + dev_warn(dev, + "swiotlb: coherent allocation failed, size=%zu\n", + size); + dump_stack(); + } + return NULL; +} + +static bool swiotlb_free_buffer(struct device *dev, size_t size, + dma_addr_t dma_addr) +{ + phys_addr_t phys_addr = dma_to_phys(dev, dma_addr); + + WARN_ON_ONCE(irqs_disabled()); + + if (!is_swiotlb_buffer(phys_addr)) + return false; + + /* + * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single. + * DMA_ATTR_SKIP_CPU_SYNC is optional. + */ + swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + return true; +} + +static void +swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir, + int do_panic) +{ + if (swiotlb_force == SWIOTLB_NO_FORCE) + return; + + /* + * Ran out of IOMMU space for this operation. This is very bad. + * Unfortunately the drivers cannot handle this operation properly. + * unless they check for dma_mapping_error (most don't) + * When the mapping is small enough return a static buffer to limit + * the damage, or panic when the transfer is too big. + */ + dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n", + size); + + if (size <= io_tlb_overflow || !do_panic) + return; + + if (dir == DMA_BIDIRECTIONAL) + panic("DMA: Random memory could be DMA accessed\n"); + if (dir == DMA_FROM_DEVICE) + panic("DMA: Random memory could be DMA written\n"); + if (dir == DMA_TO_DEVICE) + panic("DMA: Random memory could be DMA read\n"); +} + +/* + * Map a single buffer of the indicated size for DMA in streaming mode. The + * physical address to use is returned. + * + * Once the device is given the dma address, the device owns this memory until + * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed. + */ +dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + unsigned long attrs) +{ + phys_addr_t map, phys = page_to_phys(page) + offset; + dma_addr_t dev_addr = phys_to_dma(dev, phys); + + BUG_ON(dir == DMA_NONE); + /* + * If the address happens to be in the device's DMA window, + * we can safely return the device addr and not worry about bounce + * buffering it. + */ + if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE) + return dev_addr; + + trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); + + /* Oh well, have to allocate and map a bounce buffer. */ + map = map_single(dev, phys, size, dir, attrs); + if (map == SWIOTLB_MAP_ERROR) { + swiotlb_full(dev, size, dir, 1); + return __phys_to_dma(dev, io_tlb_overflow_buffer); + } + + dev_addr = __phys_to_dma(dev, map); + + /* Ensure that the address returned is DMA'ble */ + if (dma_capable(dev, dev_addr, size)) + return dev_addr; + + attrs |= DMA_ATTR_SKIP_CPU_SYNC; + swiotlb_tbl_unmap_single(dev, map, size, dir, attrs); + + return __phys_to_dma(dev, io_tlb_overflow_buffer); +} + +/* + * Unmap a single streaming mode DMA translation. The dma_addr and size must + * match what was provided for in a previous swiotlb_map_page call. All + * other usages are undefined. + * + * After this call, reads by the cpu to the buffer are guaranteed to see + * whatever the device wrote there. + */ +static void unmap_single(struct device *hwdev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); + + BUG_ON(dir == DMA_NONE); + + if (is_swiotlb_buffer(paddr)) { + swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs); + return; + } + + if (dir != DMA_FROM_DEVICE) + return; + + /* + * phys_to_virt doesn't work with hihgmem page but we could + * call dma_mark_clean() with hihgmem page here. However, we + * are fine since dma_mark_clean() is null on POWERPC. We can + * make dma_mark_clean() take a physical address if necessary. + */ + dma_mark_clean(phys_to_virt(paddr), size); +} + +void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + unmap_single(hwdev, dev_addr, size, dir, attrs); +} + +/* + * Make physical memory consistent for a single streaming mode DMA translation + * after a transfer. + * + * If you perform a swiotlb_map_page() but wish to interrogate the buffer + * using the cpu, yet do not wish to teardown the dma mapping, you must + * call this function before doing so. At the next point you give the dma + * address back to the card, you must first perform a + * swiotlb_dma_sync_for_device, and then the device again owns the buffer + */ +static void +swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + enum dma_sync_target target) +{ + phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); + + BUG_ON(dir == DMA_NONE); + + if (is_swiotlb_buffer(paddr)) { + swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); + return; + } + + if (dir != DMA_FROM_DEVICE) + return; + + dma_mark_clean(phys_to_virt(paddr), size); +} + +void +swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir) +{ + swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU); +} + +void +swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir) +{ + swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE); +} + +/* + * Map a set of buffers described by scatterlist in streaming mode for DMA. + * This is the scatter-gather version of the above swiotlb_map_page + * interface. Here the scatter gather list elements are each tagged with the + * appropriate dma address and length. They are obtained via + * sg_dma_{address,length}(SG). + * + * NOTE: An implementation may be able to use a smaller number of + * DMA address/length pairs than there are SG table elements. + * (for example via virtual mapping capabilities) + * The routine returns the number of addr/length pairs actually + * used, at most nents. + * + * Device ownership issues as mentioned above for swiotlb_map_page are the + * same here. + */ +int +swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, + enum dma_data_direction dir, unsigned long attrs) +{ + struct scatterlist *sg; + int i; + + BUG_ON(dir == DMA_NONE); + + for_each_sg(sgl, sg, nelems, i) { + phys_addr_t paddr = sg_phys(sg); + dma_addr_t dev_addr = phys_to_dma(hwdev, paddr); + + if (swiotlb_force == SWIOTLB_FORCE || + !dma_capable(hwdev, dev_addr, sg->length)) { + phys_addr_t map = map_single(hwdev, sg_phys(sg), + sg->length, dir, attrs); + if (map == SWIOTLB_MAP_ERROR) { + /* Don't panic here, we expect map_sg users + to do proper error handling. */ + swiotlb_full(hwdev, sg->length, dir, 0); + attrs |= DMA_ATTR_SKIP_CPU_SYNC; + swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir, + attrs); + sg_dma_len(sgl) = 0; + return 0; + } + sg->dma_address = __phys_to_dma(hwdev, map); + } else + sg->dma_address = dev_addr; + sg_dma_len(sg) = sg->length; + } + return nelems; +} + +/* + * Unmap a set of streaming mode DMA translations. Again, cpu read rules + * concerning calls here are the same as for swiotlb_unmap_page() above. + */ +void +swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + unsigned long attrs) +{ + struct scatterlist *sg; + int i; + + BUG_ON(dir == DMA_NONE); + + for_each_sg(sgl, sg, nelems, i) + unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, + attrs); +} + +/* + * Make physical memory consistent for a set of streaming mode DMA translations + * after a transfer. + * + * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules + * and usage. + */ +static void +swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + enum dma_sync_target target) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nelems, i) + swiotlb_sync_single(hwdev, sg->dma_address, + sg_dma_len(sg), dir, target); +} + +void +swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir) +{ + swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU); +} + +void +swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir) +{ + swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); +} + +int +swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) +{ + return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer)); +} + +/* + * Return whether the given device DMA address mask can be supported + * properly. For example, if your device can only drive the low 24-bits + * during bus mastering, then you would pass 0x00ffffff as the mask to + * this function. + */ +int +swiotlb_dma_supported(struct device *hwdev, u64 mask) +{ + return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask; +} + +void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + void *vaddr; + + /* temporary workaround: */ + if (gfp & __GFP_NOWARN) + attrs |= DMA_ATTR_NO_WARN; + + /* + * Don't print a warning when the first allocation attempt fails. + * swiotlb_alloc_coherent() will print a warning when the DMA memory + * allocation ultimately failed. + */ + gfp |= __GFP_NOWARN; + + vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs); + if (!vaddr) + vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs); + return vaddr; +} + +void swiotlb_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_addr, unsigned long attrs) +{ + if (!swiotlb_free_buffer(dev, size, dma_addr)) + dma_direct_free(dev, size, vaddr, dma_addr, attrs); +} + +const struct dma_map_ops swiotlb_dma_ops = { + .mapping_error = swiotlb_dma_mapping_error, + .alloc = swiotlb_alloc, + .free = swiotlb_free, + .sync_single_for_cpu = swiotlb_sync_single_for_cpu, + .sync_single_for_device = swiotlb_sync_single_for_device, + .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, + .sync_sg_for_device = swiotlb_sync_sg_for_device, + .map_sg = swiotlb_map_sg_attrs, + .unmap_sg = swiotlb_unmap_sg_attrs, + .map_page = swiotlb_map_page, + .unmap_page = swiotlb_unmap_page, + .dma_supported = dma_direct_supported, +}; +EXPORT_SYMBOL(swiotlb_dma_ops); diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c new file mode 100644 index 000000000000..631ddec4b60a --- /dev/null +++ b/kernel/dma/virt.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DMA operations that map to virtual addresses without flushing memory. + */ +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/dma-mapping.h> +#include <linux/scatterlist.h> + +static void *dma_virt_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, + unsigned long attrs) +{ + void *ret; + + ret = (void *)__get_free_pages(gfp, get_order(size)); + if (ret) + *dma_handle = (uintptr_t)ret; + return ret; +} + +static void dma_virt_free(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_addr, + unsigned long attrs) +{ + free_pages((unsigned long)cpu_addr, get_order(size)); +} + +static dma_addr_t dma_virt_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + unsigned long attrs) +{ + return (uintptr_t)(page_address(page) + offset); +} + +static int dma_virt_map_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, + unsigned long attrs) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sgl, sg, nents, i) { + BUG_ON(!sg_page(sg)); + sg_dma_address(sg) = (uintptr_t)sg_virt(sg); + sg_dma_len(sg) = sg->length; + } + + return nents; +} + +const struct dma_map_ops dma_virt_ops = { + .alloc = dma_virt_alloc, + .free = dma_virt_free, + .map_page = dma_virt_map_page, + .map_sg = dma_virt_map_sg, +}; +EXPORT_SYMBOL(dma_virt_ops); diff --git a/kernel/events/core.c b/kernel/events/core.c index 08f5e1b42b43..80f456ec5d89 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1656,7 +1656,7 @@ perf_event_groups_next(struct perf_event *event) typeof(*event), group_node)) /* - * Add a event from the lists for its context. + * Add an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void @@ -1844,7 +1844,7 @@ static void perf_group_attach(struct perf_event *event) } /* - * Remove a event from the lists for its context. + * Remove an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void @@ -2148,7 +2148,7 @@ static void __perf_event_disable(struct perf_event *event, } /* - * Disable a event. + * Disable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to @@ -2677,7 +2677,7 @@ static void __perf_event_enable(struct perf_event *event, } /* - * Enable a event. + * Enable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to @@ -2755,7 +2755,7 @@ static int __perf_event_stop(void *info) * events will refuse to restart because of rb::aux_mmap_count==0, * see comments in perf_aux_output_begin(). * - * Since this is happening on a event-local CPU, no trace is lost + * Since this is happening on an event-local CPU, no trace is lost * while restarting. */ if (sd->restart) @@ -4827,7 +4827,7 @@ __perf_read(struct perf_event *event, char __user *buf, size_t count) int ret; /* - * Return end-of-file for a read on a event that is in + * Return end-of-file for a read on an event that is in * error state (i.e. because it was pinned but it couldn't be * scheduled on to the CPU at some point). */ @@ -5246,8 +5246,8 @@ void perf_event_update_userpage(struct perf_event *event) userpg = rb->user_page; /* - * Disable preemption so as to not let the corresponding user-space - * spin too long if we get preempted. + * Disable preemption to guarantee consistent time stamps are stored to + * the user page. */ preempt_disable(); ++userpg->lock; @@ -5273,11 +5273,11 @@ unlock: } EXPORT_SYMBOL_GPL(perf_event_update_userpage); -static int perf_mmap_fault(struct vm_fault *vmf) +static vm_fault_t perf_mmap_fault(struct vm_fault *vmf) { struct perf_event *event = vmf->vma->vm_file->private_data; struct ring_buffer *rb; - int ret = VM_FAULT_SIGBUS; + vm_fault_t ret = VM_FAULT_SIGBUS; if (vmf->flags & FAULT_FLAG_MKWRITE) { if (vmf->pgoff == 0) @@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt) static struct perf_callchain_entry __empty_callchain = { .nr = 0, }; -static struct perf_callchain_entry * +struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs) { bool kernel = !event->attr.exclude_callchain_kernel; @@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header, if (sample_type & PERF_SAMPLE_CALLCHAIN) { int size = 1; - data->callchain = perf_callchain(event, regs); + if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY)) + data->callchain = perf_callchain(event, regs); + size += data->callchain->nr; header->size += size * sizeof(u64); @@ -6482,7 +6484,7 @@ void perf_prepare_sample(struct perf_event_header *header, data->phys_addr = perf_virt_to_phys(data->addr); } -static void __always_inline +static __always_inline void __perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs, @@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter, struct file *file, unsigned long offset, unsigned long size) { + /* d_inode(NULL) won't be equal to any mapped user-space file */ + if (!filter->path.dentry) + return false; + if (d_inode(filter->path.dentry) != file_inode(file)) return false; @@ -9898,7 +9904,7 @@ enabled: } /* - * Allocate and initialize a event structure + * Allocate and initialize an event structure */ static struct perf_event * perf_event_alloc(struct perf_event_attr *attr, int cpu, @@ -11212,6 +11218,14 @@ struct file *perf_event_get(unsigned int fd) return file; } +const struct perf_event *perf_get_event(struct file *file) +{ + if (file->f_op != &perf_fops) + return ERR_PTR(-EINVAL); + + return file->private_data; +} + const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { if (!event) @@ -11221,7 +11235,7 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event) } /* - * Inherit a event from parent task to child task. + * Inherit an event from parent task to child task. * * Returns: * - valid pointer on success diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 6e28d2866be5..b3814fce5ecb 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -345,13 +345,13 @@ void release_bp_slot(struct perf_event *bp) mutex_unlock(&nr_bp_mutex); } -static int __modify_bp_slot(struct perf_event *bp, u64 old_type) +static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { int err; __release_bp_slot(bp, old_type); - err = __reserve_bp_slot(bp, bp->attr.bp_type); + err = __reserve_bp_slot(bp, new_type); if (err) { /* * Reserve the old_type slot back in case @@ -367,12 +367,12 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type) return err; } -static int modify_bp_slot(struct perf_event *bp, u64 old_type) +static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type) { int ret; mutex_lock(&nr_bp_mutex); - ret = __modify_bp_slot(bp, old_type); + ret = __modify_bp_slot(bp, old_type, new_type); mutex_unlock(&nr_bp_mutex); return ret; } @@ -400,16 +400,18 @@ int dbg_release_bp_slot(struct perf_event *bp) return 0; } -static int validate_hw_breakpoint(struct perf_event *bp) +static int hw_breakpoint_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) { - int ret; + int err; - ret = arch_validate_hwbkpt_settings(bp); - if (ret) - return ret; + err = hw_breakpoint_arch_parse(bp, attr, hw); + if (err) + return err; - if (arch_check_bp_in_kernelspace(bp)) { - if (bp->attr.exclude_kernel) + if (arch_check_bp_in_kernelspace(hw)) { + if (attr->exclude_kernel) return -EINVAL; /* * Don't let unprivileged users set a breakpoint in the trap @@ -424,19 +426,22 @@ static int validate_hw_breakpoint(struct perf_event *bp) int register_perf_hw_breakpoint(struct perf_event *bp) { - int ret; - - ret = reserve_bp_slot(bp); - if (ret) - return ret; + struct arch_hw_breakpoint hw; + int err; - ret = validate_hw_breakpoint(bp); + err = reserve_bp_slot(bp); + if (err) + return err; - /* if arch_validate_hwbkpt_settings() fails then release bp slot */ - if (ret) + err = hw_breakpoint_parse(bp, &bp->attr, &hw); + if (err) { release_bp_slot(bp); + return err; + } - return ret; + bp->hw.info = hw; + + return 0; } /** @@ -456,35 +461,44 @@ register_user_hw_breakpoint(struct perf_event_attr *attr, } EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); +static void hw_breakpoint_copy_attr(struct perf_event_attr *to, + struct perf_event_attr *from) +{ + to->bp_addr = from->bp_addr; + to->bp_type = from->bp_type; + to->bp_len = from->bp_len; + to->disabled = from->disabled; +} + int modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr, bool check) { - u64 old_addr = bp->attr.bp_addr; - u64 old_len = bp->attr.bp_len; - int old_type = bp->attr.bp_type; - bool modify = attr->bp_type != old_type; - int err = 0; + struct arch_hw_breakpoint hw; + int err; - bp->attr.bp_addr = attr->bp_addr; - bp->attr.bp_type = attr->bp_type; - bp->attr.bp_len = attr->bp_len; + err = hw_breakpoint_parse(bp, attr, &hw); + if (err) + return err; - if (check && memcmp(&bp->attr, attr, sizeof(*attr))) - return -EINVAL; + if (check) { + struct perf_event_attr old_attr; - err = validate_hw_breakpoint(bp); - if (!err && modify) - err = modify_bp_slot(bp, old_type); + old_attr = bp->attr; + hw_breakpoint_copy_attr(&old_attr, attr); + if (memcmp(&old_attr, attr, sizeof(*attr))) + return -EINVAL; + } - if (err) { - bp->attr.bp_addr = old_addr; - bp->attr.bp_type = old_type; - bp->attr.bp_len = old_len; - return err; + if (bp->attr.bp_type != attr->bp_type) { + err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type); + if (err) + return err; } - bp->attr.disabled = attr->disabled; + hw_breakpoint_copy_attr(&bp->attr, attr); + bp->hw.info = hw; + return 0; } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 1d8ca9ea9979..5d3cf407e374 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -103,7 +103,7 @@ out: preempt_enable(); } -static bool __always_inline +static __always_inline bool ring_buffer_has_space(unsigned long head, unsigned long tail, unsigned long data_size, unsigned int size, bool backward) @@ -114,7 +114,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail, return CIRC_SPACE(tail, head, data_size) >= size; } -static int __always_inline +static __always_inline int __perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size, bool backward) @@ -414,7 +414,7 @@ err: } EXPORT_SYMBOL_GPL(perf_aux_output_begin); -static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb) +static __always_inline bool rb_need_aux_wakeup(struct ring_buffer *rb) { if (rb->aux_overwrite) return false; @@ -614,7 +614,8 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, } } - rb->aux_pages = kzalloc_node(nr_pages * sizeof(void *), GFP_KERNEL, node); + rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL, + node); if (!rb->aux_pages) return -ENOMEM; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 1725b902983f..aed1ba569954 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -918,7 +918,7 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * EXPORT_SYMBOL_GPL(uprobe_register); /* - * uprobe_apply - unregister a already registered probe. + * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: consumer which wants to add more or remove some breakpoints @@ -947,7 +947,7 @@ int uprobe_apply(struct inode *inode, loff_t offset, } /* - * uprobe_unregister - unregister a already registered probe. + * uprobe_unregister - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: identify which probe if multiple probes are colocated. @@ -1184,7 +1184,8 @@ static struct xol_area *__create_xol_area(unsigned long vaddr) if (unlikely(!area)) goto out; - area->bitmap = kzalloc(BITS_TO_LONGS(UINSNS_PER_PAGE) * sizeof(long), GFP_KERNEL); + area->bitmap = kcalloc(BITS_TO_LONGS(UINSNS_PER_PAGE), sizeof(long), + GFP_KERNEL); if (!area->bitmap) goto free_area; @@ -1402,7 +1403,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri) /* * Called with no locks held. - * Called in context of a exiting or a exec-ing thread. + * Called in context of an exiting or an exec-ing thread. */ void uprobe_free_utask(struct task_struct *t) { diff --git a/kernel/fail_function.c b/kernel/fail_function.c index 1d5632d8bbcc..bc80a4e268c0 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -184,9 +184,6 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs) if (should_fail(&fei_fault_attr, 1)) { regs_set_return_value(regs, attr->retval); override_function_with_return(regs); - /* Kprobe specific fixup */ - reset_current_kprobe(); - preempt_enable_no_resched(); return 1; } @@ -258,7 +255,7 @@ static ssize_t fei_write(struct file *file, const char __user *buffer, /* cut off if it is too long */ if (count > KSYM_NAME_LEN) count = KSYM_NAME_LEN; - buf = kmalloc(sizeof(char) * (count + 1), GFP_KERNEL); + buf = kmalloc(count + 1, GFP_KERNEL); if (!buf) return -ENOMEM; diff --git a/kernel/fork.c b/kernel/fork.c index a5d21c42acfc..33112315b5c0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -303,11 +303,36 @@ struct kmem_cache *files_cachep; struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ -struct kmem_cache *vm_area_cachep; +static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; +struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) +{ + struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + + if (vma) + vma_init(vma, mm); + return vma; +} + +struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) +{ + struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + + if (new) { + *new = *orig; + INIT_LIST_HEAD(&new->anon_vma_chain); + } + return new; +} + +void vm_area_free(struct vm_area_struct *vma) +{ + kmem_cache_free(vm_area_cachep, vma); +} + static void account_kernel_stack(struct task_struct *tsk, int account) { void *stack = task_stack_page(tsk); @@ -440,6 +465,14 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, continue; } charge = 0; + /* + * Don't duplicate many vmas if we've been oom-killed (for + * example) + */ + if (fatal_signal_pending(current)) { + retval = -EINTR; + goto out; + } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); @@ -447,11 +480,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto fail_nomem; charge = len; } - tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; - *tmp = *mpnt; - INIT_LIST_HEAD(&tmp->anon_vma_chain); retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; @@ -531,7 +562,7 @@ fail_uprobe_end: fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: - kmem_cache_free(vm_area_cachep, tmp); + vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); @@ -811,7 +842,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); -#ifdef CONFIG_CC_STACKPROTECTOR +#ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif @@ -835,6 +866,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->fail_nth = 0; #endif +#ifdef CONFIG_BLK_CGROUP + tsk->throttle_queue = NULL; + tsk->use_memdelay = 0; +#endif + return tsk; free_stack: @@ -899,6 +935,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->pinned_vm = 0; memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); + spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); @@ -1712,7 +1749,7 @@ static __latent_entropy struct task_struct *copy_process( p->start_time = ktime_get_ns(); p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; - p->audit_context = NULL; + audit_set_context(p, NULL); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); @@ -1899,6 +1936,8 @@ static __latent_entropy struct task_struct *copy_process( */ copy_seccomp(p); + rseq_fork(p, clone_flags); + /* * Process group and session signals need to be delivered to just the * parent before the fork or both the parent and the child after the @@ -2242,6 +2281,8 @@ static void sighand_ctor(void *data) void __init proc_caches_init(void) { + unsigned int mm_size; + sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| @@ -2258,15 +2299,16 @@ void __init proc_caches_init(void) sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); + /* - * FIXME! The "sizeof(struct mm_struct)" currently includes the - * whole struct cpumask for the OFFSTACK case. We could change - * this to *only* allocate as much of it as required by the - * maximum number of CPU's we can ever have. The cpumask_allocation - * is at the end of the structure, exactly for that reason. + * The mm_cpumask is located at the end of mm_struct, and is + * dynamically sized based on the maximum CPU number this system + * can have, taking hotplug into account (nr_cpu_ids). */ + mm_size = sizeof(struct mm_struct) + cpumask_size(); + mm_cachep = kmem_cache_create_usercopy("mm_struct", - sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, + mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), diff --git a/kernel/freezer.c b/kernel/freezer.c index 6f56a9e219fa..b162b74611e4 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -15,7 +15,9 @@ atomic_t system_freezing_cnt = ATOMIC_INIT(0); EXPORT_SYMBOL(system_freezing_cnt); -/* indicate whether PM freezing is in effect, protected by pm_mutex */ +/* indicate whether PM freezing is in effect, protected by + * system_transition_mutex + */ bool pm_freezing; bool pm_nosig_freezing; diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index 1276aabaab55..1e3823fa799b 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -53,23 +53,16 @@ config GCOV_PROFILE_ALL choice prompt "Specify GCOV format" depends on GCOV_KERNEL - default GCOV_FORMAT_AUTODETECT ---help--- - The gcov format is usually determined by the GCC version, but there are + The gcov format is usually determined by the GCC version, and the + default is chosen according to your GCC version. However, there are exceptions where format changes are integrated in lower-version GCCs. - In such a case use this option to adjust the format used in the kernel - accordingly. - - If unsure, choose "Autodetect". - -config GCOV_FORMAT_AUTODETECT - bool "Autodetect" - ---help--- - Select this option to use the format that corresponds to your GCC - version. + In such a case, change this option to adjust the format used in the + kernel accordingly. config GCOV_FORMAT_3_4 bool "GCC 3.4 format" + depends on CC_IS_GCC && GCC_VERSION < 40700 ---help--- Select this option to use the format defined by GCC 3.4. diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile index c6c50e5c680e..ff06d64df397 100644 --- a/kernel/gcov/Makefile +++ b/kernel/gcov/Makefile @@ -4,5 +4,3 @@ ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"' obj-y := base.o fs.o obj-$(CONFIG_GCOV_FORMAT_3_4) += gcc_3_4.o obj-$(CONFIG_GCOV_FORMAT_4_7) += gcc_4_7.o -obj-$(CONFIG_GCOV_FORMAT_AUTODETECT) += $(call cc-ifversion, -lt, 0407, \ - gcc_3_4.o, gcc_4_7.o) diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 751593ed7c0b..32b479468e4d 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -44,6 +44,7 @@ int __read_mostly sysctl_hung_task_warnings = 10; static int __read_mostly did_panic; static bool hung_task_show_lock; +static bool hung_task_call_panic; static struct task_struct *watchdog_task; @@ -127,10 +128,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) touch_nmi_watchdog(); if (sysctl_hung_task_panic) { - if (hung_task_show_lock) - debug_show_all_locks(); - trigger_all_cpu_backtrace(); - panic("hung_task: blocked tasks"); + hung_task_show_lock = true; + hung_task_call_panic = true; } } @@ -193,6 +192,10 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) rcu_read_unlock(); if (hung_task_show_lock) debug_show_all_locks(); + if (hung_task_call_panic) { + trigger_all_cpu_backtrace(); + panic("hung_task: blocked tasks"); + } } static long hung_timeout_jiffies(unsigned long last_checked, diff --git a/kernel/iomem.c b/kernel/iomem.c new file mode 100644 index 000000000000..f7525e14ebc6 --- /dev/null +++ b/kernel/iomem.c @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/device.h> +#include <linux/types.h> +#include <linux/io.h> +#include <linux/mm.h> + +#ifndef ioremap_cache +/* temporary while we convert existing ioremap_cache users to memremap */ +__weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) +{ + return ioremap(offset, size); +} +#endif + +#ifndef arch_memremap_wb +static void *arch_memremap_wb(resource_size_t offset, unsigned long size) +{ + return (__force void *)ioremap_cache(offset, size); +} +#endif + +#ifndef arch_memremap_can_ram_remap +static bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + return true; +} +#endif + +static void *try_ram_remap(resource_size_t offset, size_t size, + unsigned long flags) +{ + unsigned long pfn = PHYS_PFN(offset); + + /* In the simple case just return the existing linear address */ + if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)) && + arch_memremap_can_ram_remap(offset, size, flags)) + return __va(offset); + + return NULL; /* fallback to arch_memremap_wb */ +} + +/** + * memremap() - remap an iomem_resource as cacheable memory + * @offset: iomem resource start address + * @size: size of remap + * @flags: any of MEMREMAP_WB, MEMREMAP_WT, MEMREMAP_WC, + * MEMREMAP_ENC, MEMREMAP_DEC + * + * memremap() is "ioremap" for cases where it is known that the resource + * being mapped does not have i/o side effects and the __iomem + * annotation is not applicable. In the case of multiple flags, the different + * mapping types will be attempted in the order listed below until one of + * them succeeds. + * + * MEMREMAP_WB - matches the default mapping for System RAM on + * the architecture. This is usually a read-allocate write-back cache. + * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM + * memremap() will bypass establishing a new mapping and instead return + * a pointer into the direct map. + * + * MEMREMAP_WT - establish a mapping whereby writes either bypass the + * cache or are written through to memory and never exist in a + * cache-dirty state with respect to program visibility. Attempts to + * map System RAM with this mapping type will fail. + * + * MEMREMAP_WC - establish a writecombine mapping, whereby writes may + * be coalesced together (e.g. in the CPU's write buffers), but is otherwise + * uncached. Attempts to map System RAM with this mapping type will fail. + */ +void *memremap(resource_size_t offset, size_t size, unsigned long flags) +{ + int is_ram = region_intersects(offset, size, + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); + void *addr = NULL; + + if (!flags) + return NULL; + + if (is_ram == REGION_MIXED) { + WARN_ONCE(1, "memremap attempted on mixed range %pa size: %#lx\n", + &offset, (unsigned long) size); + return NULL; + } + + /* Try all mapping types requested until one returns non-NULL */ + if (flags & MEMREMAP_WB) { + /* + * MEMREMAP_WB is special in that it can be satisifed + * from the direct map. Some archs depend on the + * capability of memremap() to autodetect cases where + * the requested range is potentially in System RAM. + */ + if (is_ram == REGION_INTERSECTS) + addr = try_ram_remap(offset, size, flags); + if (!addr) + addr = arch_memremap_wb(offset, size); + } + + /* + * If we don't have a mapping yet and other request flags are + * present then we will be attempting to establish a new virtual + * address mapping. Enforce that this mapping is not aliasing + * System RAM. + */ + if (!addr && is_ram == REGION_INTERSECTS && flags != MEMREMAP_WB) { + WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n", + &offset, (unsigned long) size); + return NULL; + } + + if (!addr && (flags & MEMREMAP_WT)) + addr = ioremap_wt(offset, size); + + if (!addr && (flags & MEMREMAP_WC)) + addr = ioremap_wc(offset, size); + + return addr; +} +EXPORT_SYMBOL(memremap); + +void memunmap(void *addr) +{ + if (is_vmalloc_addr(addr)) + iounmap((void __iomem *) addr); +} +EXPORT_SYMBOL(memunmap); + +static void devm_memremap_release(struct device *dev, void *res) +{ + memunmap(*(void **)res); +} + +static int devm_memremap_match(struct device *dev, void *res, void *match_data) +{ + return *(void **)res == match_data; +} + +void *devm_memremap(struct device *dev, resource_size_t offset, + size_t size, unsigned long flags) +{ + void **ptr, *addr; + + ptr = devres_alloc_node(devm_memremap_release, sizeof(*ptr), GFP_KERNEL, + dev_to_node(dev)); + if (!ptr) + return ERR_PTR(-ENOMEM); + + addr = memremap(offset, size, flags); + if (addr) { + *ptr = addr; + devres_add(dev, ptr); + } else { + devres_free(ptr); + return ERR_PTR(-ENXIO); + } + + return addr; +} +EXPORT_SYMBOL(devm_memremap); + +void devm_memunmap(struct device *dev, void *addr) +{ + WARN_ON(devres_release(dev, devm_memremap_release, + devm_memremap_match, addr)); +} +EXPORT_SYMBOL(devm_memunmap); diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index c6766f326072..5f3e2baefca9 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -134,7 +134,6 @@ config GENERIC_IRQ_DEBUGFS endmenu config GENERIC_IRQ_MULTI_HANDLER - depends on !MULTI_IRQ_HANDLER bool help Allow to specify the low level IRQ handler at run time. diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 4dadeb3d6666..6f636136cccc 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -55,6 +55,7 @@ static const struct irq_bit_descr irqchip_flags[] = { BIT_MASK_DESCR(IRQCHIP_SKIP_SET_WAKE), BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE), BIT_MASK_DESCR(IRQCHIP_EOI_THREADED), + BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI), }; static void diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index afc7f902d74a..578d0e5f1b5b 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -443,6 +443,7 @@ static void free_desc(unsigned int irq) * We free the descriptor, masks and stat fields via RCU. That * allows demultiplex interrupts to do rcu based management of * the child interrupts. + * This also allows us to use rcu in kstat_irqs_usr(). */ call_rcu(&desc->rcu, delayed_free_desc); } @@ -928,17 +929,17 @@ unsigned int kstat_irqs(unsigned int irq) * kstat_irqs_usr - Get the statistics for an interrupt * @irq: The interrupt number * - * Returns the sum of interrupt counts on all cpus since boot for - * @irq. Contrary to kstat_irqs() this can be called from any - * preemptible context. It's protected against concurrent removal of - * an interrupt descriptor when sparse irqs are enabled. + * Returns the sum of interrupt counts on all cpus since boot for @irq. + * Contrary to kstat_irqs() this can be called from any context. + * It uses rcu since a concurrent removal of an interrupt descriptor is + * observing an rcu grace period before delayed_free_desc()/irq_kobj_release(). */ unsigned int kstat_irqs_usr(unsigned int irq) { unsigned int sum; - irq_lock_sparse(); + rcu_read_lock(); sum = kstat_irqs(irq); - irq_unlock_sparse(); + rcu_read_unlock(); return sum; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e3336d904f64..fb86146037a7 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -24,6 +24,7 @@ #ifdef CONFIG_IRQ_FORCED_THREADING __read_mostly bool force_irqthreads; +EXPORT_SYMBOL_GPL(force_irqthreads); static int __init setup_forced_irqthreads(char *arg) { @@ -204,6 +205,39 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, return ret; } +#ifdef CONFIG_GENERIC_PENDING_IRQ +static inline int irq_set_affinity_pending(struct irq_data *data, + const struct cpumask *dest) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + irqd_set_move_pending(data); + irq_copy_pending(desc, dest); + return 0; +} +#else +static inline int irq_set_affinity_pending(struct irq_data *data, + const struct cpumask *dest) +{ + return -EBUSY; +} +#endif + +static int irq_try_set_affinity(struct irq_data *data, + const struct cpumask *dest, bool force) +{ + int ret = irq_do_set_affinity(data, dest, force); + + /* + * In case that the underlying vector management is busy and the + * architecture supports the generic pending mechanism then utilize + * this to avoid returning an error to user space. + */ + if (ret == -EBUSY && !force) + ret = irq_set_affinity_pending(data, dest); + return ret; +} + int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -214,8 +248,8 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; - if (irq_can_move_pcntxt(data)) { - ret = irq_do_set_affinity(data, mask, force); + if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) { + ret = irq_try_set_affinity(data, mask, force); } else { irqd_set_move_pending(data); irq_copy_pending(desc, mask); @@ -756,9 +790,19 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id) static int irq_wait_for_interrupt(struct irqaction *action) { - set_current_state(TASK_INTERRUPTIBLE); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { + if (kthread_should_stop()) { + /* may need to run one last time */ + if (test_and_clear_bit(IRQTF_RUNTHREAD, + &action->thread_flags)) { + __set_current_state(TASK_RUNNING); + return 0; + } + __set_current_state(TASK_RUNNING); + return -1; + } if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) { @@ -766,10 +810,7 @@ static int irq_wait_for_interrupt(struct irqaction *action) return 0; } schedule(); - set_current_state(TASK_INTERRUPTIBLE); } - __set_current_state(TASK_RUNNING); - return -1; } /* @@ -990,11 +1031,8 @@ static int irq_thread(void *data) /* * This is the regular exit path. __free_irq() is stopping the * thread via kthread_stop() after calling - * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the - * oneshot mask bit can be set. We cannot verify that as we - * cannot touch the oneshot mask at this point anymore as - * __setup_irq() might have given out currents thread_mask - * again. + * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the + * oneshot mask bit can be set. */ task_work_cancel(current, irq_thread_dtor); return 0; @@ -1034,6 +1072,13 @@ static int irq_setup_forced_threading(struct irqaction *new) if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) return 0; + /* + * No further action required for interrupts which are requested as + * threaded interrupts already + */ + if (new->handler == irq_default_primary_handler) + return 0; + new->flags |= IRQF_ONESHOT; /* @@ -1041,7 +1086,7 @@ static int irq_setup_forced_threading(struct irqaction *new) * thread handler. We force thread them as well by creating a * secondary action. */ - if (new->handler != irq_default_primary_handler && new->thread_fn) { + if (new->handler && new->thread_fn) { /* Allocate the secondary action */ new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!new->secondary) @@ -1210,8 +1255,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) /* * Protects against a concurrent __free_irq() call which might wait - * for synchronize_irq() to complete without holding the optional - * chip bus lock and desc->lock. + * for synchronize_hardirq() to complete without holding the optional + * chip bus lock and desc->lock. Also protects against handing out + * a recycled oneshot thread_mask bit while it's still in use by + * its previous owner. */ mutex_lock(&desc->request_mutex); @@ -1530,9 +1577,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); - if (!desc) - return NULL; - mutex_lock(&desc->request_mutex); chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); @@ -1579,11 +1623,11 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) /* * Drop bus_lock here so the changes which were done in the chip * callbacks above are synced out to the irq chips which hang - * behind a slow bus (I2C, SPI) before calling synchronize_irq(). + * behind a slow bus (I2C, SPI) before calling synchronize_hardirq(). * * Aside of that the bus_lock can also be taken from the threaded * handler in irq_finalize_oneshot() which results in a deadlock - * because synchronize_irq() would wait forever for the thread to + * because kthread_stop() would wait forever for the thread to * complete, which is blocked on the bus lock. * * The still held desc->request_mutex() protects against a @@ -1595,7 +1639,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) unregister_handler_proc(irq, action); /* Make sure it's not being used on another CPU: */ - synchronize_irq(irq); + synchronize_hardirq(irq); #ifdef CONFIG_DEBUG_SHIRQ /* @@ -1604,7 +1648,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) * is so by doing an extra call to the handler .... * * ( We do this after actually deregistering it, to make sure that a - * 'real' IRQ doesn't run in * parallel with our fake. ) + * 'real' IRQ doesn't run in parallel with our fake. ) */ if (action->flags & IRQF_SHARED) { local_irq_save(flags); @@ -1613,6 +1657,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id) } #endif + /* + * The action has already been removed above, but the thread writes + * its oneshot mask bit when it completes. Though request_mutex is + * held across this which prevents __setup_irq() from handing out + * the same bit to a newly requested action. + */ if (action->thread) { kthread_stop(action->thread); put_task_struct(action->thread); diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 86ae0eb80b53..def48589ea48 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -38,17 +38,18 @@ bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear) void irq_move_masked_irq(struct irq_data *idata) { struct irq_desc *desc = irq_data_to_desc(idata); - struct irq_chip *chip = desc->irq_data.chip; + struct irq_data *data = &desc->irq_data; + struct irq_chip *chip = data->chip; - if (likely(!irqd_is_setaffinity_pending(&desc->irq_data))) + if (likely(!irqd_is_setaffinity_pending(data))) return; - irqd_clr_move_pending(&desc->irq_data); + irqd_clr_move_pending(data); /* * Paranoia: cpu-local interrupts shouldn't be calling in here anyway. */ - if (irqd_is_per_cpu(&desc->irq_data)) { + if (irqd_is_per_cpu(data)) { WARN_ON(1); return; } @@ -73,13 +74,24 @@ void irq_move_masked_irq(struct irq_data *idata) * For correct operation this depends on the caller * masking the irqs. */ - if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) - irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false); - + if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) { + int ret; + + ret = irq_do_set_affinity(data, desc->pending_mask, false); + /* + * If the there is a cleanup pending in the underlying + * vector management, reschedule the move for the next + * interrupt. Leave desc->pending_mask intact. + */ + if (ret == -EBUSY) { + irqd_set_move_pending(data); + return; + } + } cpumask_clear(desc->pending_mask); } -void irq_move_irq(struct irq_data *idata) +void __irq_move_irq(struct irq_data *idata) { bool masked; @@ -90,9 +102,6 @@ void irq_move_irq(struct irq_data *idata) */ idata = irq_desc_get_irq_data(irq_data_to_desc(idata)); - if (likely(!irqd_is_setaffinity_pending(idata))) - return; - if (unlikely(irqd_irq_disabled(idata))) return; diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 37eda10f5c36..da9addb8d655 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -475,22 +475,24 @@ int show_interrupts(struct seq_file *p, void *v) seq_putc(p, '\n'); } - irq_lock_sparse(); + rcu_read_lock(); desc = irq_to_desc(i); if (!desc) goto outsparse; - raw_spin_lock_irqsave(&desc->lock, flags); - for_each_online_cpu(j) - any_count |= kstat_irqs_cpu(i, j); - action = desc->action; - if ((!action || irq_desc_is_chained(desc)) && !any_count) - goto out; + if (desc->kstat_irqs) + for_each_online_cpu(j) + any_count |= *per_cpu_ptr(desc->kstat_irqs, j); + + if ((!desc->action || irq_desc_is_chained(desc)) && !any_count) + goto outsparse; seq_printf(p, "%*d: ", prec, i); for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); + seq_printf(p, "%10u ", desc->kstat_irqs ? + *per_cpu_ptr(desc->kstat_irqs, j) : 0); + raw_spin_lock_irqsave(&desc->lock, flags); if (desc->irq_data.chip) { if (desc->irq_data.chip->irq_print_chip) desc->irq_data.chip->irq_print_chip(&desc->irq_data, p); @@ -511,6 +513,7 @@ int show_interrupts(struct seq_file *p, void *v) if (desc->name) seq_printf(p, "-%-8s", desc->name); + action = desc->action; if (action) { seq_printf(p, " %s", action->name); while ((action = action->next) != NULL) @@ -518,10 +521,9 @@ int show_interrupts(struct seq_file *p, void *v) } seq_putc(p, '\n'); -out: raw_spin_unlock_irqrestore(&desc->lock, flags); outsparse: - irq_unlock_sparse(); + rcu_read_unlock(); return 0; } #endif diff --git a/kernel/kcov.c b/kernel/kcov.c index 2c16f1ab5e10..3ebd09efe72a 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -58,7 +58,7 @@ struct kcov { static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) { - enum kcov_mode mode; + unsigned int mode; /* * We are interested in code coverage as a function of a syscall inputs, @@ -241,7 +241,8 @@ static void kcov_put(struct kcov *kcov) void kcov_task_init(struct task_struct *t) { - t->kcov_mode = KCOV_MODE_DISABLED; + WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED); + barrier(); t->kcov_size = 0; t->kcov_area = NULL; t->kcov = NULL; @@ -323,6 +324,21 @@ static int kcov_close(struct inode *inode, struct file *filep) return 0; } +/* + * Fault in a lazily-faulted vmalloc area before it can be used by + * __santizer_cov_trace_pc(), to avoid recursion issues if any code on the + * vmalloc fault handling path is instrumented. + */ +static void kcov_fault_in_area(struct kcov *kcov) +{ + unsigned long stride = PAGE_SIZE / sizeof(unsigned long); + unsigned long *area = kcov->area; + unsigned long offset; + + for (offset = 0; offset < kcov->size; offset += stride) + READ_ONCE(area[offset]); +} + static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, unsigned long arg) { @@ -371,6 +387,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, #endif else return -EINVAL; + kcov_fault_in_area(kcov); /* Cache in task struct for performance. */ t->kcov_size = kcov->size; t->kcov_area = kcov->area; diff --git a/kernel/kexec.c b/kernel/kexec.c index aed8fb2564b3..68559808fdfa 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -11,6 +11,7 @@ #include <linux/capability.h> #include <linux/mm.h> #include <linux/file.h> +#include <linux/security.h> #include <linux/kexec.h> #include <linux/mutex.h> #include <linux/list.h> @@ -195,10 +196,17 @@ out: static inline int kexec_load_check(unsigned long nr_segments, unsigned long flags) { + int result; + /* We only trust the superuser with rebooting the system. */ if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) return -EPERM; + /* Permit LSMs and IMA to fail the kexec */ + result = security_kernel_load_data(LOADING_KEXEC_IMAGE); + if (result < 0) + return result; + /* * Verify we have a legal set of flags * This leaves us room for future extensions. diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 20fef1a38602..23a83a4da38a 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -829,6 +829,8 @@ static int kimage_load_normal_segment(struct kimage *image, else buf += mchunk; mbytes -= mchunk; + + cond_resched(); } out: return result; @@ -893,6 +895,8 @@ static int kimage_load_crash_segment(struct kimage *image, else buf += mchunk; mbytes -= mchunk; + + cond_resched(); } out: return result; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 75d8e7cf040e..c6a3b6851372 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -793,7 +793,7 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi, * The section headers in kexec_purgatory are read-only. In order to * have them modifiable make a temporary copy. */ - sechdrs = vzalloc(pi->ehdr->e_shnum * sizeof(Elf_Shdr)); + sechdrs = vzalloc(array_size(sizeof(Elf_Shdr), pi->ehdr->e_shnum)); if (!sechdrs) return -ENOMEM; memcpy(sechdrs, (void *)pi->ehdr + pi->ehdr->e_shoff, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ea619021d901..ab257be4d924 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -627,8 +627,8 @@ static void optimize_kprobe(struct kprobe *p) (kprobe_disabled(p) || kprobes_all_disarmed)) return; - /* Both of break_handler and post_handler are not supported. */ - if (p->break_handler || p->post_handler) + /* kprobes with post_handler can not be optimized */ + if (p->post_handler) return; op = container_of(p, struct optimized_kprobe, kp); @@ -710,9 +710,7 @@ static void reuse_unused_kprobe(struct kprobe *ap) * there is still a relative jump) and disabled. */ op = container_of(ap, struct optimized_kprobe, kp); - if (unlikely(list_empty(&op->list))) - printk(KERN_WARNING "Warning: found a stray unused " - "aggrprobe@%p\n", ap->addr); + WARN_ON_ONCE(list_empty(&op->list)); /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ @@ -985,7 +983,8 @@ static int arm_kprobe_ftrace(struct kprobe *p) ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 0, 0); if (ret) { - pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n", + p->addr, ret); return ret; } @@ -1025,7 +1024,8 @@ static int disarm_kprobe_ftrace(struct kprobe *p) ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0); - WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); + WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n", + p->addr, ret); return ret; } #else /* !CONFIG_KPROBES_ON_FTRACE */ @@ -1116,20 +1116,6 @@ static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, } NOKPROBE_SYMBOL(aggr_fault_handler); -static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs) -{ - struct kprobe *cur = __this_cpu_read(kprobe_instance); - int ret = 0; - - if (cur && cur->break_handler) { - if (cur->break_handler(cur, regs)) - ret = 1; - } - reset_kprobe_instance(); - return ret; -} -NOKPROBE_SYMBOL(aggr_break_handler); - /* Walks the list and increments nmissed count for multiprobe case */ void kprobes_inc_nmissed_count(struct kprobe *p) { @@ -1270,24 +1256,15 @@ static void cleanup_rp_inst(struct kretprobe *rp) } NOKPROBE_SYMBOL(cleanup_rp_inst); -/* -* Add the new probe to ap->list. Fail if this is the -* second jprobe at the address - two jprobes can't coexist -*/ +/* Add the new probe to ap->list */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { BUG_ON(kprobe_gone(ap) || kprobe_gone(p)); - if (p->break_handler || p->post_handler) + if (p->post_handler) unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */ - if (p->break_handler) { - if (ap->break_handler) - return -EEXIST; - list_add_tail_rcu(&p->list, &ap->list); - ap->break_handler = aggr_break_handler; - } else - list_add_rcu(&p->list, &ap->list); + list_add_rcu(&p->list, &ap->list); if (p->post_handler && !ap->post_handler) ap->post_handler = aggr_post_handler; @@ -1310,8 +1287,6 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) /* We don't care the kprobe which has gone. */ if (p->post_handler && !kprobe_gone(p)) ap->post_handler = aggr_post_handler; - if (p->break_handler && !kprobe_gone(p)) - ap->break_handler = aggr_break_handler; INIT_LIST_HEAD(&ap->list); INIT_HLIST_NODE(&ap->hlist); @@ -1706,8 +1681,6 @@ static int __unregister_kprobe_top(struct kprobe *p) goto disarmed; else { /* If disabling probe has special handlers, update aggrprobe */ - if (p->break_handler && !kprobe_gone(p)) - ap->break_handler = NULL; if (p->post_handler && !kprobe_gone(p)) { list_for_each_entry_rcu(list_p, &ap->list, list) { if ((list_p != p) && (list_p->post_handler)) @@ -1812,77 +1785,6 @@ unsigned long __weak arch_deref_entry_point(void *entry) return (unsigned long)entry; } -#if 0 -int register_jprobes(struct jprobe **jps, int num) -{ - int ret = 0, i; - - if (num <= 0) - return -EINVAL; - - for (i = 0; i < num; i++) { - ret = register_jprobe(jps[i]); - - if (ret < 0) { - if (i > 0) - unregister_jprobes(jps, i); - break; - } - } - - return ret; -} -EXPORT_SYMBOL_GPL(register_jprobes); - -int register_jprobe(struct jprobe *jp) -{ - unsigned long addr, offset; - struct kprobe *kp = &jp->kp; - - /* - * Verify probepoint as well as the jprobe handler are - * valid function entry points. - */ - addr = arch_deref_entry_point(jp->entry); - - if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 && - kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) { - kp->pre_handler = setjmp_pre_handler; - kp->break_handler = longjmp_break_handler; - return register_kprobe(kp); - } - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(register_jprobe); - -void unregister_jprobe(struct jprobe *jp) -{ - unregister_jprobes(&jp, 1); -} -EXPORT_SYMBOL_GPL(unregister_jprobe); - -void unregister_jprobes(struct jprobe **jps, int num) -{ - int i; - - if (num <= 0) - return; - mutex_lock(&kprobe_mutex); - for (i = 0; i < num; i++) - if (__unregister_kprobe_top(&jps[i]->kp) < 0) - jps[i]->kp.addr = NULL; - mutex_unlock(&kprobe_mutex); - - synchronize_sched(); - for (i = 0; i < num; i++) { - if (jps[i]->kp.addr) - __unregister_kprobe_bottom(&jps[i]->kp); - } -} -EXPORT_SYMBOL_GPL(unregister_jprobes); -#endif - #ifdef CONFIG_KRETPROBES /* * This kprobe pre_handler is registered with every kretprobe. When probe @@ -1982,7 +1884,6 @@ int register_kretprobe(struct kretprobe *rp) rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; rp->kp.fault_handler = NULL; - rp->kp.break_handler = NULL; /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { @@ -2105,7 +2006,6 @@ static void kill_kprobe(struct kprobe *p) list_for_each_entry_rcu(kp, &p->list, list) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; - p->break_handler = NULL; kill_optimized_kprobe(p); } /* @@ -2169,11 +2069,12 @@ out: } EXPORT_SYMBOL_GPL(enable_kprobe); +/* Caller must NOT call this in usual path. This is only for critical case */ void dump_kprobe(struct kprobe *kp) { - printk(KERN_WARNING "Dumping kprobe:\n"); - printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n", - kp->symbol_name, kp->addr, kp->offset); + pr_err("Dumping kprobe:\n"); + pr_err("Name: %s\nOffset: %x\nAddress: %pS\n", + kp->symbol_name, kp->offset, kp->addr); } NOKPROBE_SYMBOL(dump_kprobe); @@ -2196,11 +2097,8 @@ static int __init populate_kprobe_blacklist(unsigned long *start, entry = arch_deref_entry_point((void *)*iter); if (!kernel_text_address(entry) || - !kallsyms_lookup_size_offset(entry, &size, &offset)) { - pr_err("Failed to find blacklist at %p\n", - (void *)entry); + !kallsyms_lookup_size_offset(entry, &size, &offset)) continue; - } ent = kmalloc(sizeof(*ent), GFP_KERNEL); if (!ent) @@ -2326,21 +2224,23 @@ static void report_probe(struct seq_file *pi, struct kprobe *p, const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; + void *addr = p->addr; if (p->pre_handler == pre_handler_kretprobe) kprobe_type = "r"; - else if (p->pre_handler == setjmp_pre_handler) - kprobe_type = "j"; else kprobe_type = "k"; + if (!kallsyms_show_value()) + addr = NULL; + if (sym) - seq_printf(pi, "%p %s %s+0x%x %s ", - p->addr, kprobe_type, sym, offset, + seq_printf(pi, "%px %s %s+0x%x %s ", + addr, kprobe_type, sym, offset, (modname ? modname : " ")); - else - seq_printf(pi, "%p %s %p ", - p->addr, kprobe_type, p->addr); + else /* try to use %pS */ + seq_printf(pi, "%px %s %pS ", + addr, kprobe_type, p->addr); if (!pp) pp = p; @@ -2428,8 +2328,16 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) struct kprobe_blacklist_entry *ent = list_entry(v, struct kprobe_blacklist_entry, list); - seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, - (void *)ent->end_addr, (void *)ent->start_addr); + /* + * If /proc/kallsyms is not showing kernel address, we won't + * show them here either. + */ + if (!kallsyms_show_value()) + seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL, + (void *)ent->start_addr); + else + seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, + (void *)ent->end_addr, (void *)ent->start_addr); return 0; } @@ -2611,7 +2519,7 @@ static int __init debugfs_kprobe_init(void) if (!dir) return -ENOMEM; - file = debugfs_create_file("list", 0444, dir, NULL, + file = debugfs_create_file("list", 0400, dir, NULL, &debugfs_kprobes_operations); if (!file) goto error; @@ -2621,7 +2529,7 @@ static int __init debugfs_kprobe_init(void) if (!file) goto error; - file = debugfs_create_file("blacklist", 0444, dir, NULL, + file = debugfs_create_file("blacklist", 0400, dir, NULL, &debugfs_kprobe_blacklist_ops); if (!file) goto error; @@ -2637,6 +2545,3 @@ late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ module_init(init_kprobes); - -/* defined in arch/.../kernel/kprobes.c */ -EXPORT_SYMBOL_GPL(jprobe_return); diff --git a/kernel/kthread.c b/kernel/kthread.c index 481951bf091d..087d18d771b5 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -177,9 +177,20 @@ void *kthread_probe_data(struct task_struct *task) static void __kthread_parkme(struct kthread *self) { for (;;) { - set_current_state(TASK_PARKED); + /* + * TASK_PARKED is a special state; we must serialize against + * possible pending wakeups to avoid store-store collisions on + * task->state. + * + * Such a collision might possibly result in the task state + * changin from TASK_PARKED and us failing the + * wait_task_inactive() in kthread_park(). + */ + set_special_state(TASK_PARKED); if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; + + complete(&self->parked); schedule(); } __set_current_state(TASK_RUNNING); @@ -191,11 +202,6 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); -void kthread_park_complete(struct task_struct *k) -{ - complete_all(&to_kthread(k)->parked); -} - static int kthread(void *_create) { /* Copy data: it's on kthread's stack */ @@ -319,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), task = create->result; if (!IS_ERR(task)) { static const struct sched_param param = { .sched_priority = 0 }; + char name[TASK_COMM_LEN]; - vsnprintf(task->comm, sizeof(task->comm), namefmt, args); + /* + * task is already visible to other tasks, so updating + * COMM must be protected. + */ + vsnprintf(name, sizeof(name), namefmt, args); + set_task_comm(task, name); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. @@ -459,8 +471,10 @@ void kthread_unpark(struct task_struct *k) if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); - reinit_completion(&kthread->parked); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + /* + * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup. + */ wake_up_state(k, TASK_PARKED); } EXPORT_SYMBOL_GPL(kthread_unpark); @@ -484,10 +498,22 @@ int kthread_park(struct task_struct *k) if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; + if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) + return -EBUSY; + set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); + /* + * Wait for __kthread_parkme() to complete(), this means we + * _will_ have TASK_PARKED and are about to call schedule(). + */ wait_for_completion(&kthread->parked); + /* + * Now wait for that schedule() to complete and the task to + * get scheduled out. + */ + WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED)); } return 0; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index edcac5de7ebc..5fa4d3138bf1 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1265,11 +1265,11 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class) this.parent = NULL; this.class = class; - local_irq_save(flags); + raw_local_irq_save(flags); arch_spin_lock(&lockdep_lock); ret = __lockdep_count_forward_deps(&this); arch_spin_unlock(&lockdep_lock); - local_irq_restore(flags); + raw_local_irq_restore(flags); return ret; } @@ -1292,11 +1292,11 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class) this.parent = NULL; this.class = class; - local_irq_save(flags); + raw_local_irq_save(flags); arch_spin_lock(&lockdep_lock); ret = __lockdep_count_backward_deps(&this); arch_spin_unlock(&lockdep_lock); - local_irq_restore(flags); + raw_local_irq_restore(flags); return ret; } @@ -4411,7 +4411,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) if (unlikely(!debug_locks)) return; - local_irq_save(flags); + raw_local_irq_save(flags); for (i = 0; i < curr->lockdep_depth; i++) { hlock = curr->held_locks + i; @@ -4422,7 +4422,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock); break; } - local_irq_restore(flags); + raw_local_irq_restore(flags); } EXPORT_SYMBOL_GPL(debug_check_no_locks_freed); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 6850ffd69125..57bef4fbfb31 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -21,6 +21,9 @@ * Davidlohr Bueso <dave@stgolabs.net> * Based on kernel/rcu/torture.c. */ + +#define pr_fmt(fmt) fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/kthread.h> @@ -57,7 +60,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable."); torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s"); torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable"); -torture_param(bool, verbose, true, +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); static char *torture_type = "spin_lock"; @@ -913,7 +916,9 @@ static int __init lock_torture_init(void) /* Initialize the statistics so that each run gets its own numbers. */ if (nwriters_stress) { lock_is_write_held = 0; - cxt.lwsa = kmalloc(sizeof(*cxt.lwsa) * cxt.nrealwriters_stress, GFP_KERNEL); + cxt.lwsa = kmalloc_array(cxt.nrealwriters_stress, + sizeof(*cxt.lwsa), + GFP_KERNEL); if (cxt.lwsa == NULL) { VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory"); firsterr = -ENOMEM; @@ -942,7 +947,9 @@ static int __init lock_torture_init(void) if (nreaders_stress) { lock_is_read_held = 0; - cxt.lrsa = kmalloc(sizeof(*cxt.lrsa) * cxt.nrealreaders_stress, GFP_KERNEL); + cxt.lrsa = kmalloc_array(cxt.nrealreaders_stress, + sizeof(*cxt.lrsa), + GFP_KERNEL); if (cxt.lrsa == NULL) { VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory"); firsterr = -ENOMEM; @@ -985,7 +992,8 @@ static int __init lock_torture_init(void) } if (nwriters_stress) { - writer_tasks = kzalloc(cxt.nrealwriters_stress * sizeof(writer_tasks[0]), + writer_tasks = kcalloc(cxt.nrealwriters_stress, + sizeof(writer_tasks[0]), GFP_KERNEL); if (writer_tasks == NULL) { VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory"); @@ -995,7 +1003,8 @@ static int __init lock_torture_init(void) } if (cxt.cur_ops->readlock) { - reader_tasks = kzalloc(cxt.nrealreaders_stress * sizeof(reader_tasks[0]), + reader_tasks = kcalloc(cxt.nrealreaders_stress, + sizeof(reader_tasks[0]), GFP_KERNEL); if (reader_tasks == NULL) { VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory"); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 4f014be7a4b8..2823d4163a37 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1465,6 +1465,29 @@ rt_mutex_fastunlock(struct rt_mutex *lock, rt_mutex_postunlock(&wake_q); } +static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) +{ + might_sleep(); + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +/** + * rt_mutex_lock_nested - lock a rt_mutex + * + * @lock: the rt_mutex to be locked + * @subclass: the lockdep subclass + */ +void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) +{ + __rt_mutex_lock(lock, subclass); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); +#endif + +#ifndef CONFIG_DEBUG_LOCK_ALLOC /** * rt_mutex_lock - lock a rt_mutex * @@ -1472,12 +1495,10 @@ rt_mutex_fastunlock(struct rt_mutex *lock, */ void __sched rt_mutex_lock(struct rt_mutex *lock) { - might_sleep(); - - mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); + __rt_mutex_lock(lock, 0); } EXPORT_SYMBOL_GPL(rt_mutex_lock); +#endif /** * rt_mutex_lock_interruptible - lock a rt_mutex interruptible diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index bc1e507be9ff..776308d2fa9e 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -181,6 +181,7 @@ void down_read_non_owner(struct rw_semaphore *sem) might_sleep(); __down_read(sem); + rwsem_set_reader_owned(sem); } EXPORT_SYMBOL(down_read_non_owner); diff --git a/kernel/memremap.c b/kernel/memremap.c index 895e6b76b25e..38283363da06 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -1,15 +1,5 @@ -/* - * Copyright(c) 2015 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2015 Intel Corporation. All rights reserved. */ #include <linux/radix-tree.h> #include <linux/device.h> #include <linux/types.h> @@ -19,170 +9,8 @@ #include <linux/memory_hotplug.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/wait_bit.h> -#ifndef ioremap_cache -/* temporary while we convert existing ioremap_cache users to memremap */ -__weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) -{ - return ioremap(offset, size); -} -#endif - -#ifndef arch_memremap_wb -static void *arch_memremap_wb(resource_size_t offset, unsigned long size) -{ - return (__force void *)ioremap_cache(offset, size); -} -#endif - -#ifndef arch_memremap_can_ram_remap -static bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, - unsigned long flags) -{ - return true; -} -#endif - -static void *try_ram_remap(resource_size_t offset, size_t size, - unsigned long flags) -{ - unsigned long pfn = PHYS_PFN(offset); - - /* In the simple case just return the existing linear address */ - if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)) && - arch_memremap_can_ram_remap(offset, size, flags)) - return __va(offset); - - return NULL; /* fallback to arch_memremap_wb */ -} - -/** - * memremap() - remap an iomem_resource as cacheable memory - * @offset: iomem resource start address - * @size: size of remap - * @flags: any of MEMREMAP_WB, MEMREMAP_WT, MEMREMAP_WC, - * MEMREMAP_ENC, MEMREMAP_DEC - * - * memremap() is "ioremap" for cases where it is known that the resource - * being mapped does not have i/o side effects and the __iomem - * annotation is not applicable. In the case of multiple flags, the different - * mapping types will be attempted in the order listed below until one of - * them succeeds. - * - * MEMREMAP_WB - matches the default mapping for System RAM on - * the architecture. This is usually a read-allocate write-back cache. - * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM - * memremap() will bypass establishing a new mapping and instead return - * a pointer into the direct map. - * - * MEMREMAP_WT - establish a mapping whereby writes either bypass the - * cache or are written through to memory and never exist in a - * cache-dirty state with respect to program visibility. Attempts to - * map System RAM with this mapping type will fail. - * - * MEMREMAP_WC - establish a writecombine mapping, whereby writes may - * be coalesced together (e.g. in the CPU's write buffers), but is otherwise - * uncached. Attempts to map System RAM with this mapping type will fail. - */ -void *memremap(resource_size_t offset, size_t size, unsigned long flags) -{ - int is_ram = region_intersects(offset, size, - IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); - void *addr = NULL; - - if (!flags) - return NULL; - - if (is_ram == REGION_MIXED) { - WARN_ONCE(1, "memremap attempted on mixed range %pa size: %#lx\n", - &offset, (unsigned long) size); - return NULL; - } - - /* Try all mapping types requested until one returns non-NULL */ - if (flags & MEMREMAP_WB) { - /* - * MEMREMAP_WB is special in that it can be satisifed - * from the direct map. Some archs depend on the - * capability of memremap() to autodetect cases where - * the requested range is potentially in System RAM. - */ - if (is_ram == REGION_INTERSECTS) - addr = try_ram_remap(offset, size, flags); - if (!addr) - addr = arch_memremap_wb(offset, size); - } - - /* - * If we don't have a mapping yet and other request flags are - * present then we will be attempting to establish a new virtual - * address mapping. Enforce that this mapping is not aliasing - * System RAM. - */ - if (!addr && is_ram == REGION_INTERSECTS && flags != MEMREMAP_WB) { - WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n", - &offset, (unsigned long) size); - return NULL; - } - - if (!addr && (flags & MEMREMAP_WT)) - addr = ioremap_wt(offset, size); - - if (!addr && (flags & MEMREMAP_WC)) - addr = ioremap_wc(offset, size); - - return addr; -} -EXPORT_SYMBOL(memremap); - -void memunmap(void *addr) -{ - if (is_vmalloc_addr(addr)) - iounmap((void __iomem *) addr); -} -EXPORT_SYMBOL(memunmap); - -static void devm_memremap_release(struct device *dev, void *res) -{ - memunmap(*(void **)res); -} - -static int devm_memremap_match(struct device *dev, void *res, void *match_data) -{ - return *(void **)res == match_data; -} - -void *devm_memremap(struct device *dev, resource_size_t offset, - size_t size, unsigned long flags) -{ - void **ptr, *addr; - - ptr = devres_alloc_node(devm_memremap_release, sizeof(*ptr), GFP_KERNEL, - dev_to_node(dev)); - if (!ptr) - return ERR_PTR(-ENOMEM); - - addr = memremap(offset, size, flags); - if (addr) { - *ptr = addr; - devres_add(dev, ptr); - } else { - devres_free(ptr); - return ERR_PTR(-ENXIO); - } - - return addr; -} -EXPORT_SYMBOL(devm_memremap); - -void devm_memunmap(struct device *dev, void *addr) -{ - WARN_ON(devres_release(dev, devm_memremap_release, - devm_memremap_match, addr)); -} -EXPORT_SYMBOL(devm_memunmap); - -#ifdef CONFIG_ZONE_DEVICE static DEFINE_MUTEX(pgmap_lock); static RADIX_TREE(pgmap_radix, GFP_KERNEL); #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) @@ -348,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) unsigned long pfn, pgoff, order; pgprot_t pgprot = PAGE_KERNEL; int error, nid, is_ram; + struct dev_pagemap *conflict_pgmap; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) - align_start; + align_end = align_start + align_size - 1; + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + is_ram = region_intersects(align_start, align_size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); @@ -371,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) mutex_lock(&pgmap_lock); error = 0; - align_end = align_start + align_size - 1; foreach_order_pgoff(res, order, pgoff) { error = __radix_tree_insert(&pgmap_radix, @@ -473,10 +317,32 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, return pgmap; } -#endif /* CONFIG_ZONE_DEVICE */ +EXPORT_SYMBOL_GPL(get_dev_pagemap); + +#ifdef CONFIG_DEV_PAGEMAP_OPS +DEFINE_STATIC_KEY_FALSE(devmap_managed_key); +EXPORT_SYMBOL(devmap_managed_key); +static atomic_t devmap_enable; + +/* + * Toggle the static key for ->page_free() callbacks when dev_pagemap + * pages go idle. + */ +void dev_pagemap_get_ops(void) +{ + if (atomic_inc_return(&devmap_enable) == 1) + static_branch_enable(&devmap_managed_key); +} +EXPORT_SYMBOL_GPL(dev_pagemap_get_ops); + +void dev_pagemap_put_ops(void) +{ + if (atomic_dec_and_test(&devmap_enable)) + static_branch_disable(&devmap_managed_key); +} +EXPORT_SYMBOL_GPL(dev_pagemap_put_ops); -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) -void put_zone_device_private_or_public_page(struct page *page) +void __put_devmap_managed_page(struct page *page) { int count = page_ref_dec_return(page); @@ -496,5 +362,5 @@ void put_zone_device_private_or_public_page(struct page *page) } else if (!count) __put_page(page); } -EXPORT_SYMBOL(put_zone_device_private_or_public_page); -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ +EXPORT_SYMBOL(__put_devmap_managed_page); +#endif /* CONFIG_DEV_PAGEMAP_OPS */ diff --git a/kernel/module.c b/kernel/module.c index c9bea7f2b43e..a7615d661910 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -274,9 +274,7 @@ static void module_assert_mutex_or_preempt(void) } static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE); -#ifndef CONFIG_MODULE_SIG_FORCE module_param(sig_enforce, bool_enable_only, 0644); -#endif /* !CONFIG_MODULE_SIG_FORCE */ /* * Export sig_enforce kernel cmdline parameter to allow other subsystems rely @@ -1604,8 +1602,7 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info) if (notes == 0) return; - notes_attrs = kzalloc(sizeof(*notes_attrs) - + notes * sizeof(notes_attrs->attrs[0]), + notes_attrs = kzalloc(struct_size(notes_attrs, attrs, notes), GFP_KERNEL); if (notes_attrs == NULL) return; @@ -2786,7 +2783,7 @@ static int module_sig_check(struct load_info *info, int flags) } /* Not having a signature is only an error if we're strict. */ - if (err == -ENOKEY && !sig_enforce) + if (err == -ENOKEY && !is_module_sig_enforced()) err = 0; return err; @@ -2879,7 +2876,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len, if (info->len < sizeof(*(info->hdr))) return -ENOEXEC; - err = security_kernel_read_file(NULL, READING_MODULE); + err = security_kernel_load_data(LOADING_MODULE); if (err) return err; diff --git a/kernel/panic.c b/kernel/panic.c index 42e487488554..8b2e002d52eb 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -623,7 +623,7 @@ static __init int register_warn_debugfs(void) device_initcall(register_warn_debugfs); #endif -#ifdef CONFIG_CC_STACKPROTECTOR +#ifdef CONFIG_STACKPROTECTOR /* * Called when gcc's -fstack-protector feature is used, and diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 9c85c7822383..abef759de7c8 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -338,7 +338,7 @@ static int create_image(int platform_mode) * hibernation_snapshot - Quiesce devices and create a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. * - * This routine must be called with pm_mutex held. + * This routine must be called with system_transition_mutex held. */ int hibernation_snapshot(int platform_mode) { @@ -500,8 +500,9 @@ static int resume_target_kernel(bool platform_mode) * hibernation_restore - Quiesce devices and restore from a hibernation image. * @platform_mode: If set, use platform driver to prepare for the transition. * - * This routine must be called with pm_mutex held. If it is successful, control - * reappears in the restored target kernel in hibernation_snapshot(). + * This routine must be called with system_transition_mutex held. If it is + * successful, control reappears in the restored target kernel in + * hibernation_snapshot(). */ int hibernation_restore(int platform_mode) { @@ -638,6 +639,7 @@ static void power_down(void) break; case HIBERNATION_PLATFORM: hibernation_platform_enter(); + /* Fall through */ case HIBERNATION_SHUTDOWN: if (pm_power_off) kernel_power_off(); @@ -805,13 +807,13 @@ static int software_resume(void) * name_to_dev_t() below takes a sysfs buffer mutex when sysfs * is configured into the kernel. Since the regular hibernate * trigger path is via sysfs which takes a buffer mutex before - * calling hibernate functions (which take pm_mutex) this can - * cause lockdep to complain about a possible ABBA deadlock + * calling hibernate functions (which take system_transition_mutex) + * this can cause lockdep to complain about a possible ABBA deadlock * which cannot happen since we're in the boot code here and * sysfs can't be invoked yet. Therefore, we use a subclass * here to avoid lockdep complaining. */ - mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING); + mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING); if (swsusp_resume_device) goto Check_image; @@ -899,7 +901,7 @@ static int software_resume(void) atomic_inc(&snapshot_device_available); /* For success case, the suspend path will release the lock */ Unlock: - mutex_unlock(&pm_mutex); + mutex_unlock(&system_transition_mutex); pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: diff --git a/kernel/power/main.c b/kernel/power/main.c index 705c2366dafe..35b50823d83b 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -15,17 +15,16 @@ #include <linux/workqueue.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/suspend.h> #include "power.h" -DEFINE_MUTEX(pm_mutex); - #ifdef CONFIG_PM_SLEEP void lock_system_sleep(void) { current->flags |= PF_FREEZER_SKIP; - mutex_lock(&pm_mutex); + mutex_lock(&system_transition_mutex); } EXPORT_SYMBOL_GPL(lock_system_sleep); @@ -37,8 +36,9 @@ void unlock_system_sleep(void) * * Reason: * Fundamentally, we just don't need it, because freezing condition - * doesn't come into effect until we release the pm_mutex lock, - * since the freezer always works with pm_mutex held. + * doesn't come into effect until we release the + * system_transition_mutex lock, since the freezer always works with + * system_transition_mutex held. * * More importantly, in the case of hibernation, * unlock_system_sleep() gets called in snapshot_read() and @@ -47,7 +47,7 @@ void unlock_system_sleep(void) * enter the refrigerator, thus causing hibernation to lockup. */ current->flags &= ~PF_FREEZER_SKIP; - mutex_unlock(&pm_mutex); + mutex_unlock(&system_transition_mutex); } EXPORT_SYMBOL_GPL(unlock_system_sleep); @@ -455,8 +455,9 @@ struct kobject *power_kobj; * state - control system sleep states. * * show() returns available sleep state labels, which may be "mem", "standby", - * "freeze" and "disk" (hibernation). See Documentation/power/states.txt for a - * description of what they mean. + * "freeze" and "disk" (hibernation). + * See Documentation/admin-guide/pm/sleep-states.rst for a description of + * what they mean. * * store() accepts one of those strings, translates it into the proper * enumerated value, and initiates a suspend transition. diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 87331565e505..5342f6fc022e 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -92,7 +92,7 @@ static void s2idle_enter(void) /* Push all the CPUs into the idle loop. */ wake_up_all_idle_cpus(); /* Make the current CPU wait so it can enter the idle loop too. */ - swait_event(s2idle_wait_head, + swait_event_exclusive(s2idle_wait_head, s2idle_state == S2IDLE_STATE_WAKE); cpuidle_pause(); @@ -160,7 +160,7 @@ void s2idle_wake(void) raw_spin_lock_irqsave(&s2idle_lock, flags); if (s2idle_state > S2IDLE_STATE_NONE) { s2idle_state = S2IDLE_STATE_WAKE; - swake_up(&s2idle_wait_head); + swake_up_one(&s2idle_wait_head); } raw_spin_unlock_irqrestore(&s2idle_lock, flags); } @@ -556,7 +556,7 @@ static int enter_state(suspend_state_t state) } else if (!valid_state(state)) { return -EINVAL; } - if (!mutex_trylock(&pm_mutex)) + if (!mutex_trylock(&system_transition_mutex)) return -EBUSY; if (state == PM_SUSPEND_TO_IDLE) @@ -590,7 +590,7 @@ static int enter_state(suspend_state_t state) pm_pr_dbg("Finishing wakeup.\n"); suspend_finish(); Unlock: - mutex_unlock(&pm_mutex); + mutex_unlock(&system_transition_mutex); return error; } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 1efcb5b0c3ed..d7f6c1a288d3 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -698,7 +698,7 @@ static int save_image_lzo(struct swap_map_handle *handle, goto out_clean; } - data = vmalloc(sizeof(*data) * nr_threads); + data = vmalloc(array_size(nr_threads, sizeof(*data))); if (!data) { pr_err("Failed to allocate LZO data\n"); ret = -ENOMEM; @@ -923,7 +923,7 @@ int swsusp_write(unsigned int flags) } memset(&snapshot, 0, sizeof(struct snapshot_handle)); error = snapshot_read_next(&snapshot); - if (error < PAGE_SIZE) { + if (error < (int)PAGE_SIZE) { if (error >= 0) error = -EFAULT; @@ -1183,14 +1183,14 @@ static int load_image_lzo(struct swap_map_handle *handle, nr_threads = num_online_cpus() - 1; nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); - page = vmalloc(sizeof(*page) * LZO_MAX_RD_PAGES); + page = vmalloc(array_size(LZO_MAX_RD_PAGES, sizeof(*page))); if (!page) { pr_err("Failed to allocate LZO page\n"); ret = -ENOMEM; goto out_clean; } - data = vmalloc(sizeof(*data) * nr_threads); + data = vmalloc(array_size(nr_threads, sizeof(*data))); if (!data) { pr_err("Failed to allocate LZO data\n"); ret = -ENOMEM; @@ -1483,7 +1483,7 @@ int swsusp_read(unsigned int *flags_p) memset(&snapshot, 0, sizeof(struct snapshot_handle)); error = snapshot_write_next(&snapshot); - if (error < PAGE_SIZE) + if (error < (int)PAGE_SIZE) return error < 0 ? error : -EFAULT; header = (struct swsusp_info *)data_of(snapshot); error = get_swap_reader(&handle, flags_p); diff --git a/kernel/power/user.c b/kernel/power/user.c index abd225550271..2d8b60a3c86b 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -216,7 +216,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!mutex_trylock(&pm_mutex)) + if (!mutex_trylock(&system_transition_mutex)) return -EBUSY; lock_device_hotplug(); @@ -394,7 +394,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, } unlock_device_hotplug(); - mutex_unlock(&pm_mutex); + mutex_unlock(&system_transition_mutex); return error; } diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 40cea6735c2d..4d04683c31b2 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -91,7 +91,17 @@ static inline void rcu_seq_end(unsigned long *sp) WRITE_ONCE(*sp, rcu_seq_endval(sp)); } -/* Take a snapshot of the update side's sequence number. */ +/* + * rcu_seq_snap - Take a snapshot of the update side's sequence number. + * + * This function returns the earliest value of the grace-period sequence number + * that will indicate that a full grace period has elapsed since the current + * time. Once the grace-period sequence number has reached this value, it will + * be safe to invoke all callbacks that have been registered prior to the + * current time. This value is the current grace-period number plus two to the + * power of the number of low-order bits reserved for state, then rounded up to + * the next value in which the state bits are all zero. + */ static inline unsigned long rcu_seq_snap(unsigned long *sp) { unsigned long s; @@ -108,6 +118,15 @@ static inline unsigned long rcu_seq_current(unsigned long *sp) } /* + * Given a snapshot from rcu_seq_snap(), determine whether or not the + * corresponding update-side operation has started. + */ +static inline bool rcu_seq_started(unsigned long *sp, unsigned long s) +{ + return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp)); +} + +/* * Given a snapshot from rcu_seq_snap(), determine whether or not a * full update-side operation has occurred. */ @@ -117,6 +136,45 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s) } /* + * Has a grace period completed since the time the old gp_seq was collected? + */ +static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new) +{ + return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK); +} + +/* + * Has a grace period started since the time the old gp_seq was collected? + */ +static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new) +{ + return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK, + new); +} + +/* + * Roughly how many full grace periods have elapsed between the collection + * of the two specified grace periods? + */ +static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old) +{ + unsigned long rnd_diff; + + if (old == new) + return 0; + /* + * Compute the number of grace periods (still shifted up), plus + * one if either of new and old is not an exact grace period. + */ + rnd_diff = (new & ~RCU_SEQ_STATE_MASK) - + ((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) + + ((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK)); + if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff)) + return 1; /* Definitely no grace period has elapsed. */ + return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2; +} + +/* * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally * by call_rcu() and rcu callback execution, and are therefore not part of the * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. @@ -276,6 +334,9 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt) /* Is this rcu_node a leaf? */ #define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1) +/* Is this rcu_node the last leaf? */ +#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1]) + /* * Do a full breadth-first scan of the rcu_node structures for the * specified rcu_state structure. @@ -405,8 +466,7 @@ enum rcutorture_type { #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed); -void rcutorture_record_test_transition(void); + unsigned long *gp_seq); void rcutorture_record_progress(unsigned long vernum); void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, @@ -415,15 +475,11 @@ void do_trace_rcu_torture_read(const char *rcutorturename, unsigned long c); #else static inline void rcutorture_get_gp_data(enum rcutorture_type test_type, - int *flags, - unsigned long *gpnum, - unsigned long *completed) + int *flags, unsigned long *gp_seq) { *flags = 0; - *gpnum = 0; - *completed = 0; + *gp_seq = 0; } -static inline void rcutorture_record_test_transition(void) { } static inline void rcutorture_record_progress(unsigned long vernum) { } #ifdef CONFIG_RCU_TRACE void do_trace_rcu_torture_read(const char *rcutorturename, @@ -441,31 +497,26 @@ void do_trace_rcu_torture_read(const char *rcutorturename, static inline void srcutorture_get_gp_data(enum rcutorture_type test_type, struct srcu_struct *sp, int *flags, - unsigned long *gpnum, - unsigned long *completed) + unsigned long *gp_seq) { if (test_type != SRCU_FLAVOR) return; *flags = 0; - *completed = sp->srcu_idx; - *gpnum = *completed; + *gp_seq = sp->srcu_idx; } #elif defined(CONFIG_TREE_SRCU) void srcutorture_get_gp_data(enum rcutorture_type test_type, struct srcu_struct *sp, int *flags, - unsigned long *gpnum, unsigned long *completed); + unsigned long *gp_seq); #endif #ifdef CONFIG_TINY_RCU -static inline unsigned long rcu_batches_started(void) { return 0; } -static inline unsigned long rcu_batches_started_bh(void) { return 0; } -static inline unsigned long rcu_batches_started_sched(void) { return 0; } -static inline unsigned long rcu_batches_completed(void) { return 0; } -static inline unsigned long rcu_batches_completed_bh(void) { return 0; } -static inline unsigned long rcu_batches_completed_sched(void) { return 0; } +static inline unsigned long rcu_get_gp_seq(void) { return 0; } +static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; } +static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; } static inline unsigned long rcu_exp_batches_completed(void) { return 0; } static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; } static inline unsigned long @@ -474,19 +525,16 @@ static inline void rcu_force_quiescent_state(void) { } static inline void rcu_bh_force_quiescent_state(void) { } static inline void rcu_sched_force_quiescent_state(void) { } static inline void show_rcu_gp_kthreads(void) { } +static inline int rcu_get_gp_kthreads_prio(void) { return 0; } #else /* #ifdef CONFIG_TINY_RCU */ -extern unsigned long rcutorture_testseq; -extern unsigned long rcutorture_vernum; -unsigned long rcu_batches_started(void); -unsigned long rcu_batches_started_bh(void); -unsigned long rcu_batches_started_sched(void); -unsigned long rcu_batches_completed(void); -unsigned long rcu_batches_completed_bh(void); -unsigned long rcu_batches_completed_sched(void); +unsigned long rcu_get_gp_seq(void); +unsigned long rcu_bh_get_gp_seq(void); +unsigned long rcu_sched_get_gp_seq(void); unsigned long rcu_exp_batches_completed(void); unsigned long rcu_exp_batches_completed_sched(void); unsigned long srcu_batches_completed(struct srcu_struct *sp); void show_rcu_gp_kthreads(void); +int rcu_get_gp_kthreads_prio(void); void rcu_force_quiescent_state(void); void rcu_bh_force_quiescent_state(void); void rcu_sched_force_quiescent_state(void); diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index e232846516b3..34244523550e 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -19,6 +19,9 @@ * * Authors: Paul E. McKenney <paulmck@us.ibm.com> */ + +#define pr_fmt(fmt) fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -88,7 +91,7 @@ torture_param(int, nreaders, -1, "Number of RCU reader threads"); torture_param(int, nwriters, -1, "Number of RCU updater threads"); torture_param(bool, shutdown, !IS_ENABLED(MODULE), "Shutdown at end of performance tests."); -torture_param(bool, verbose, true, "Enable verbose debugging printk()s"); +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); static char *perf_type = "rcu"; @@ -135,8 +138,8 @@ struct rcu_perf_ops { void (*cleanup)(void); int (*readlock)(void); void (*readunlock)(int idx); - unsigned long (*started)(void); - unsigned long (*completed)(void); + unsigned long (*get_gp_seq)(void); + unsigned long (*gp_diff)(unsigned long new, unsigned long old); unsigned long (*exp_completed)(void); void (*async)(struct rcu_head *head, rcu_callback_t func); void (*gp_barrier)(void); @@ -176,8 +179,8 @@ static struct rcu_perf_ops rcu_ops = { .init = rcu_sync_perf_init, .readlock = rcu_perf_read_lock, .readunlock = rcu_perf_read_unlock, - .started = rcu_batches_started, - .completed = rcu_batches_completed, + .get_gp_seq = rcu_get_gp_seq, + .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed, .async = call_rcu, .gp_barrier = rcu_barrier, @@ -206,8 +209,8 @@ static struct rcu_perf_ops rcu_bh_ops = { .init = rcu_sync_perf_init, .readlock = rcu_bh_perf_read_lock, .readunlock = rcu_bh_perf_read_unlock, - .started = rcu_batches_started_bh, - .completed = rcu_batches_completed_bh, + .get_gp_seq = rcu_bh_get_gp_seq, + .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed_sched, .async = call_rcu_bh, .gp_barrier = rcu_barrier_bh, @@ -263,8 +266,8 @@ static struct rcu_perf_ops srcu_ops = { .init = rcu_sync_perf_init, .readlock = srcu_perf_read_lock, .readunlock = srcu_perf_read_unlock, - .started = NULL, - .completed = srcu_perf_completed, + .get_gp_seq = srcu_perf_completed, + .gp_diff = rcu_seq_diff, .exp_completed = srcu_perf_completed, .async = srcu_call_rcu, .gp_barrier = srcu_rcu_barrier, @@ -292,8 +295,8 @@ static struct rcu_perf_ops srcud_ops = { .cleanup = srcu_sync_perf_cleanup, .readlock = srcu_perf_read_lock, .readunlock = srcu_perf_read_unlock, - .started = NULL, - .completed = srcu_perf_completed, + .get_gp_seq = srcu_perf_completed, + .gp_diff = rcu_seq_diff, .exp_completed = srcu_perf_completed, .async = srcu_call_rcu, .gp_barrier = srcu_rcu_barrier, @@ -322,8 +325,8 @@ static struct rcu_perf_ops sched_ops = { .init = rcu_sync_perf_init, .readlock = sched_perf_read_lock, .readunlock = sched_perf_read_unlock, - .started = rcu_batches_started_sched, - .completed = rcu_batches_completed_sched, + .get_gp_seq = rcu_sched_get_gp_seq, + .gp_diff = rcu_seq_diff, .exp_completed = rcu_exp_batches_completed_sched, .async = call_rcu_sched, .gp_barrier = rcu_barrier_sched, @@ -350,8 +353,8 @@ static struct rcu_perf_ops tasks_ops = { .init = rcu_sync_perf_init, .readlock = tasks_perf_read_lock, .readunlock = tasks_perf_read_unlock, - .started = rcu_no_completed, - .completed = rcu_no_completed, + .get_gp_seq = rcu_no_completed, + .gp_diff = rcu_seq_diff, .async = call_rcu_tasks, .gp_barrier = rcu_barrier_tasks, .sync = synchronize_rcu_tasks, @@ -359,9 +362,11 @@ static struct rcu_perf_ops tasks_ops = { .name = "tasks" }; -static bool __maybe_unused torturing_tasks(void) +static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old) { - return cur_ops == &tasks_ops; + if (!cur_ops->gp_diff) + return new - old; + return cur_ops->gp_diff(new, old); } /* @@ -444,8 +449,7 @@ rcu_perf_writer(void *arg) b_rcu_perf_writer_started = cur_ops->exp_completed() / 2; } else { - b_rcu_perf_writer_started = - cur_ops->completed(); + b_rcu_perf_writer_started = cur_ops->get_gp_seq(); } } @@ -502,7 +506,7 @@ retry: cur_ops->exp_completed() / 2; } else { b_rcu_perf_writer_finished = - cur_ops->completed(); + cur_ops->get_gp_seq(); } if (shutdown) { smp_mb(); /* Assign before wake. */ @@ -527,7 +531,7 @@ retry: return 0; } -static inline void +static void rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag) { pr_alert("%s" PERF_FLAG @@ -582,8 +586,8 @@ rcu_perf_cleanup(void) t_rcu_perf_writer_finished - t_rcu_perf_writer_started, ngps, - b_rcu_perf_writer_finished - - b_rcu_perf_writer_started); + rcuperf_seq_diff(b_rcu_perf_writer_finished, + b_rcu_perf_writer_started)); for (i = 0; i < nrealwriters; i++) { if (!writer_durations) break; @@ -671,12 +675,11 @@ rcu_perf_init(void) break; } if (i == ARRAY_SIZE(perf_ops)) { - pr_alert("rcu-perf: invalid perf type: \"%s\"\n", - perf_type); + pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type); pr_alert("rcu-perf types:"); for (i = 0; i < ARRAY_SIZE(perf_ops); i++) - pr_alert(" %s", perf_ops[i]->name); - pr_alert("\n"); + pr_cont(" %s", perf_ops[i]->name); + pr_cont("\n"); firsterr = -EINVAL; goto unwind; } diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index e628fcfd1bde..c596c6f1e457 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -22,6 +22,9 @@ * * See also: Documentation/RCU/torture.txt */ + +#define pr_fmt(fmt) fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -52,6 +55,7 @@ #include <linux/torture.h> #include <linux/vmalloc.h> #include <linux/sched/debug.h> +#include <linux/sched/sysctl.h> #include "rcu.h" @@ -59,6 +63,19 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>"); +/* Bits for ->extendables field, extendables param, and related definitions. */ +#define RCUTORTURE_RDR_SHIFT 8 /* Put SRCU index in upper bits. */ +#define RCUTORTURE_RDR_MASK ((1 << RCUTORTURE_RDR_SHIFT) - 1) +#define RCUTORTURE_RDR_BH 0x1 /* Extend readers by disabling bh. */ +#define RCUTORTURE_RDR_IRQ 0x2 /* ... disabling interrupts. */ +#define RCUTORTURE_RDR_PREEMPT 0x4 /* ... disabling preemption. */ +#define RCUTORTURE_RDR_RCU 0x8 /* ... entering another RCU reader. */ +#define RCUTORTURE_RDR_NBITS 4 /* Number of bits defined above. */ +#define RCUTORTURE_MAX_EXTEND (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \ + RCUTORTURE_RDR_PREEMPT) +#define RCUTORTURE_RDR_MAX_LOOPS 0x7 /* Maximum reader extensions. */ + /* Must be power of two minus one. */ + torture_param(int, cbflood_inter_holdoff, HZ, "Holdoff between floods (jiffies)"); torture_param(int, cbflood_intra_holdoff, 1, @@ -66,6 +83,8 @@ torture_param(int, cbflood_intra_holdoff, 1, torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable"); torture_param(int, cbflood_n_per_burst, 20000, "# callbacks per burst in flood"); +torture_param(int, extendables, RCUTORTURE_MAX_EXTEND, + "Extend readers by disabling bh (1), irqs (2), or preempt (4)"); torture_param(int, fqs_duration, 0, "Duration of fqs bursts (us), 0 to disable"); torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)"); @@ -84,7 +103,7 @@ torture_param(int, object_debug, 0, "Enable debug-object double call_rcu() testing"); torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); torture_param(int, onoff_interval, 0, - "Time between CPU hotplugs (s), 0=disable"); + "Time between CPU hotplugs (jiffies), 0=disable"); torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles"); torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); @@ -101,7 +120,7 @@ torture_param(int, test_boost_interval, 7, "Interval between boost tests, seconds."); torture_param(bool, test_no_idle_hz, true, "Test support for tickless idle CPUs"); -torture_param(bool, verbose, true, +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); static char *torture_type = "rcu"; @@ -148,9 +167,9 @@ static long n_rcu_torture_boost_ktrerror; static long n_rcu_torture_boost_rterror; static long n_rcu_torture_boost_failure; static long n_rcu_torture_boosts; -static long n_rcu_torture_timers; +static atomic_long_t n_rcu_torture_timers; static long n_barrier_attempts; -static long n_barrier_successes; +static long n_barrier_successes; /* did rcu_barrier test succeed? */ static atomic_long_t n_cbfloods; static struct list_head rcu_torture_removed; @@ -261,8 +280,8 @@ struct rcu_torture_ops { int (*readlock)(void); void (*read_delay)(struct torture_random_state *rrsp); void (*readunlock)(int idx); - unsigned long (*started)(void); - unsigned long (*completed)(void); + unsigned long (*get_gp_seq)(void); + unsigned long (*gp_diff)(unsigned long new, unsigned long old); void (*deferred_free)(struct rcu_torture *p); void (*sync)(void); void (*exp_sync)(void); @@ -274,6 +293,8 @@ struct rcu_torture_ops { void (*stats)(void); int irq_capable; int can_boost; + int extendables; + int ext_irq_conflict; const char *name; }; @@ -302,10 +323,10 @@ static void rcu_read_delay(struct torture_random_state *rrsp) * force_quiescent_state. */ if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) { - started = cur_ops->completed(); + started = cur_ops->get_gp_seq(); ts = rcu_trace_clock_local(); mdelay(longdelay_ms); - completed = cur_ops->completed(); + completed = cur_ops->get_gp_seq(); do_trace_rcu_torture_read(cur_ops->name, NULL, ts, started, completed); } @@ -397,8 +418,8 @@ static struct rcu_torture_ops rcu_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, .readunlock = rcu_torture_read_unlock, - .started = rcu_batches_started, - .completed = rcu_batches_completed, + .get_gp_seq = rcu_get_gp_seq, + .gp_diff = rcu_seq_diff, .deferred_free = rcu_torture_deferred_free, .sync = synchronize_rcu, .exp_sync = synchronize_rcu_expedited, @@ -439,8 +460,8 @@ static struct rcu_torture_ops rcu_bh_ops = { .readlock = rcu_bh_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_bh_torture_read_unlock, - .started = rcu_batches_started_bh, - .completed = rcu_batches_completed_bh, + .get_gp_seq = rcu_bh_get_gp_seq, + .gp_diff = rcu_seq_diff, .deferred_free = rcu_bh_torture_deferred_free, .sync = synchronize_rcu_bh, .exp_sync = synchronize_rcu_bh_expedited, @@ -449,6 +470,8 @@ static struct rcu_torture_ops rcu_bh_ops = { .fqs = rcu_bh_force_quiescent_state, .stats = NULL, .irq_capable = 1, + .extendables = (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ), + .ext_irq_conflict = RCUTORTURE_RDR_RCU, .name = "rcu_bh" }; @@ -483,8 +506,7 @@ static struct rcu_torture_ops rcu_busted_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_torture_read_unlock, - .started = rcu_no_completed, - .completed = rcu_no_completed, + .get_gp_seq = rcu_no_completed, .deferred_free = rcu_busted_torture_deferred_free, .sync = synchronize_rcu_busted, .exp_sync = synchronize_rcu_busted, @@ -572,8 +594,7 @@ static struct rcu_torture_ops srcu_ops = { .readlock = srcu_torture_read_lock, .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock, - .started = NULL, - .completed = srcu_torture_completed, + .get_gp_seq = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, .exp_sync = srcu_torture_synchronize_expedited, @@ -610,8 +631,7 @@ static struct rcu_torture_ops srcud_ops = { .readlock = srcu_torture_read_lock, .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock, - .started = NULL, - .completed = srcu_torture_completed, + .get_gp_seq = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, .exp_sync = srcu_torture_synchronize_expedited, @@ -622,6 +642,26 @@ static struct rcu_torture_ops srcud_ops = { .name = "srcud" }; +/* As above, but broken due to inappropriate reader extension. */ +static struct rcu_torture_ops busted_srcud_ops = { + .ttype = SRCU_FLAVOR, + .init = srcu_torture_init, + .cleanup = srcu_torture_cleanup, + .readlock = srcu_torture_read_lock, + .read_delay = rcu_read_delay, + .readunlock = srcu_torture_read_unlock, + .get_gp_seq = srcu_torture_completed, + .deferred_free = srcu_torture_deferred_free, + .sync = srcu_torture_synchronize, + .exp_sync = srcu_torture_synchronize_expedited, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, + .stats = srcu_torture_stats, + .irq_capable = 1, + .extendables = RCUTORTURE_MAX_EXTEND, + .name = "busted_srcud" +}; + /* * Definitions for sched torture testing. */ @@ -648,8 +688,8 @@ static struct rcu_torture_ops sched_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .started = rcu_batches_started_sched, - .completed = rcu_batches_completed_sched, + .get_gp_seq = rcu_sched_get_gp_seq, + .gp_diff = rcu_seq_diff, .deferred_free = rcu_sched_torture_deferred_free, .sync = synchronize_sched, .exp_sync = synchronize_sched_expedited, @@ -660,6 +700,7 @@ static struct rcu_torture_ops sched_ops = { .fqs = rcu_sched_force_quiescent_state, .stats = NULL, .irq_capable = 1, + .extendables = RCUTORTURE_MAX_EXTEND, .name = "sched" }; @@ -687,8 +728,7 @@ static struct rcu_torture_ops tasks_ops = { .readlock = tasks_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = tasks_torture_read_unlock, - .started = rcu_no_completed, - .completed = rcu_no_completed, + .get_gp_seq = rcu_no_completed, .deferred_free = rcu_tasks_torture_deferred_free, .sync = synchronize_rcu_tasks, .exp_sync = synchronize_rcu_tasks, @@ -700,6 +740,13 @@ static struct rcu_torture_ops tasks_ops = { .name = "tasks" }; +static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old) +{ + if (!cur_ops->gp_diff) + return new - old; + return cur_ops->gp_diff(new, old); +} + static bool __maybe_unused torturing_tasks(void) { return cur_ops == &tasks_ops; @@ -726,6 +773,44 @@ static void rcu_torture_boost_cb(struct rcu_head *head) smp_store_release(&rbip->inflight, 0); } +static int old_rt_runtime = -1; + +static void rcu_torture_disable_rt_throttle(void) +{ + /* + * Disable RT throttling so that rcutorture's boost threads don't get + * throttled. Only possible if rcutorture is built-in otherwise the + * user should manually do this by setting the sched_rt_period_us and + * sched_rt_runtime sysctls. + */ + if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime != -1) + return; + + old_rt_runtime = sysctl_sched_rt_runtime; + sysctl_sched_rt_runtime = -1; +} + +static void rcu_torture_enable_rt_throttle(void) +{ + if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime == -1) + return; + + sysctl_sched_rt_runtime = old_rt_runtime; + old_rt_runtime = -1; +} + +static bool rcu_torture_boost_failed(unsigned long start, unsigned long end) +{ + if (end - start > test_boost_duration * HZ - HZ / 2) { + VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed"); + n_rcu_torture_boost_failure++; + + return true; /* failed */ + } + + return false; /* passed */ +} + static int rcu_torture_boost(void *arg) { unsigned long call_rcu_time; @@ -746,6 +831,21 @@ static int rcu_torture_boost(void *arg) init_rcu_head_on_stack(&rbi.rcu); /* Each pass through the following loop does one boost-test cycle. */ do { + /* Track if the test failed already in this test interval? */ + bool failed = false; + + /* Increment n_rcu_torture_boosts once per boost-test */ + while (!kthread_should_stop()) { + if (mutex_trylock(&boost_mutex)) { + n_rcu_torture_boosts++; + mutex_unlock(&boost_mutex); + break; + } + schedule_timeout_uninterruptible(1); + } + if (kthread_should_stop()) + goto checkwait; + /* Wait for the next test interval. */ oldstarttime = boost_starttime; while (ULONG_CMP_LT(jiffies, oldstarttime)) { @@ -764,11 +864,10 @@ static int rcu_torture_boost(void *arg) /* RCU core before ->inflight = 1. */ smp_store_release(&rbi.inflight, 1); call_rcu(&rbi.rcu, rcu_torture_boost_cb); - if (jiffies - call_rcu_time > - test_boost_duration * HZ - HZ / 2) { - VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed"); - n_rcu_torture_boost_failure++; - } + /* Check if the boost test failed */ + failed = failed || + rcu_torture_boost_failed(call_rcu_time, + jiffies); call_rcu_time = jiffies; } stutter_wait("rcu_torture_boost"); @@ -777,6 +876,14 @@ static int rcu_torture_boost(void *arg) } /* + * If boost never happened, then inflight will always be 1, in + * this case the boost check would never happen in the above + * loop so do another one here. + */ + if (!failed && smp_load_acquire(&rbi.inflight)) + rcu_torture_boost_failed(call_rcu_time, jiffies); + + /* * Set the start time of the next test interval. * Yes, this is vulnerable to long delays, but such * delays simply cause a false negative for the next @@ -788,7 +895,6 @@ static int rcu_torture_boost(void *arg) if (mutex_trylock(&boost_mutex)) { boost_starttime = jiffies + test_boost_interval * HZ; - n_rcu_torture_boosts++; mutex_unlock(&boost_mutex); break; } @@ -831,8 +937,9 @@ rcu_torture_cbflood(void *arg) cbflood_intra_holdoff > 0 && cur_ops->call && cur_ops->cb_barrier) { - rhp = vmalloc(sizeof(*rhp) * - cbflood_n_burst * cbflood_n_per_burst); + rhp = vmalloc(array3_size(cbflood_n_burst, + cbflood_n_per_burst, + sizeof(*rhp))); err = !rhp; } if (err) { @@ -1009,7 +1116,7 @@ rcu_torture_writer(void *arg) break; } } - rcutorture_record_progress(++rcu_torture_current_version); + rcu_torture_current_version++; /* Cycle through nesting levels of rcu_expedite_gp() calls. */ if (can_expedite && !(torture_random(&rand) & 0xff & (!!expediting - 1))) { @@ -1083,27 +1190,133 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp) } /* - * RCU torture reader from timer handler. Dereferences rcu_torture_current, - * incrementing the corresponding element of the pipeline array. The - * counter in the element should never be greater than 1, otherwise, the - * RCU implementation is broken. + * Do one extension of an RCU read-side critical section using the + * current reader state in readstate (set to zero for initial entry + * to extended critical section), set the new state as specified by + * newstate (set to zero for final exit from extended critical section), + * and random-number-generator state in trsp. If this is neither the + * beginning or end of the critical section and if there was actually a + * change, do a ->read_delay(). */ -static void rcu_torture_timer(struct timer_list *unused) +static void rcutorture_one_extend(int *readstate, int newstate, + struct torture_random_state *trsp) +{ + int idxnew = -1; + int idxold = *readstate; + int statesnew = ~*readstate & newstate; + int statesold = *readstate & ~newstate; + + WARN_ON_ONCE(idxold < 0); + WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1); + + /* First, put new protection in place to avoid critical-section gap. */ + if (statesnew & RCUTORTURE_RDR_BH) + local_bh_disable(); + if (statesnew & RCUTORTURE_RDR_IRQ) + local_irq_disable(); + if (statesnew & RCUTORTURE_RDR_PREEMPT) + preempt_disable(); + if (statesnew & RCUTORTURE_RDR_RCU) + idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT; + + /* Next, remove old protection, irq first due to bh conflict. */ + if (statesold & RCUTORTURE_RDR_IRQ) + local_irq_enable(); + if (statesold & RCUTORTURE_RDR_BH) + local_bh_enable(); + if (statesold & RCUTORTURE_RDR_PREEMPT) + preempt_enable(); + if (statesold & RCUTORTURE_RDR_RCU) + cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT); + + /* Delay if neither beginning nor end and there was a change. */ + if ((statesnew || statesold) && *readstate && newstate) + cur_ops->read_delay(trsp); + + /* Update the reader state. */ + if (idxnew == -1) + idxnew = idxold & ~RCUTORTURE_RDR_MASK; + WARN_ON_ONCE(idxnew < 0); + WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1); + *readstate = idxnew | newstate; + WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0); + WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1); +} + +/* Return the biggest extendables mask given current RCU and boot parameters. */ +static int rcutorture_extend_mask_max(void) +{ + int mask; + + WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND); + mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables; + mask = mask | RCUTORTURE_RDR_RCU; + return mask; +} + +/* Return a random protection state mask, but with at least one bit set. */ +static int +rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) +{ + int mask = rcutorture_extend_mask_max(); + unsigned long randmask1 = torture_random(trsp) >> 8; + unsigned long randmask2 = randmask1 >> 1; + + WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT); + /* Half the time lots of bits, half the time only one bit. */ + if (randmask1 & 0x1) + mask = mask & randmask2; + else + mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS)); + if ((mask & RCUTORTURE_RDR_IRQ) && + !(mask & RCUTORTURE_RDR_BH) && + (oldmask & RCUTORTURE_RDR_BH)) + mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */ + if ((mask & RCUTORTURE_RDR_IRQ) && + !(mask & cur_ops->ext_irq_conflict) && + (oldmask & cur_ops->ext_irq_conflict)) + mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */ + return mask ?: RCUTORTURE_RDR_RCU; +} + +/* + * Do a randomly selected number of extensions of an existing RCU read-side + * critical section. + */ +static void rcutorture_loop_extend(int *readstate, + struct torture_random_state *trsp) +{ + int i; + int mask = rcutorture_extend_mask_max(); + + WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */ + if (!((mask - 1) & mask)) + return; /* Current RCU flavor not extendable. */ + i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS; + while (i--) { + mask = rcutorture_extend_mask(*readstate, trsp); + rcutorture_one_extend(readstate, mask, trsp); + } +} + +/* + * Do one read-side critical section, returning false if there was + * no data to read. Can be invoked both from process context and + * from a timer handler. + */ +static bool rcu_torture_one_read(struct torture_random_state *trsp) { - int idx; unsigned long started; unsigned long completed; - static DEFINE_TORTURE_RANDOM(rand); - static DEFINE_SPINLOCK(rand_lock); + int newstate; struct rcu_torture *p; int pipe_count; + int readstate = 0; unsigned long long ts; - idx = cur_ops->readlock(); - if (cur_ops->started) - started = cur_ops->started(); - else - started = cur_ops->completed(); + newstate = rcutorture_extend_mask(readstate, trsp); + rcutorture_one_extend(&readstate, newstate, trsp); + started = cur_ops->get_gp_seq(); ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || @@ -1111,39 +1324,50 @@ static void rcu_torture_timer(struct timer_list *unused) srcu_read_lock_held(srcu_ctlp) || torturing_tasks()); if (p == NULL) { - /* Leave because rcu_torture_writer is not yet underway */ - cur_ops->readunlock(idx); - return; + /* Wait for rcu_torture_writer to get underway */ + rcutorture_one_extend(&readstate, 0, trsp); + return false; } if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); - spin_lock(&rand_lock); - cur_ops->read_delay(&rand); - n_rcu_torture_timers++; - spin_unlock(&rand_lock); + rcutorture_loop_extend(&readstate, trsp); preempt_disable(); pipe_count = p->rtort_pipe_count; if (pipe_count > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - completed = cur_ops->completed(); + completed = cur_ops->get_gp_seq(); if (pipe_count > 1) { - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts, - started, completed); + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, + ts, started, completed); rcu_ftrace_dump(DUMP_ALL); } __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed - started; - if (cur_ops->started) - completed++; + completed = rcutorture_seq_diff(completed, started); if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; } __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); - cur_ops->readunlock(idx); + rcutorture_one_extend(&readstate, 0, trsp); + WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK); + return true; +} + +static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand); + +/* + * RCU torture reader from timer handler. Dereferences rcu_torture_current, + * incrementing the corresponding element of the pipeline array. The + * counter in the element should never be greater than 1, otherwise, the + * RCU implementation is broken. + */ +static void rcu_torture_timer(struct timer_list *unused) +{ + atomic_long_inc(&n_rcu_torture_timers); + (void)rcu_torture_one_read(this_cpu_ptr(&rcu_torture_timer_rand)); /* Test call_rcu() invocation from interrupt handler. */ if (cur_ops->call) { @@ -1163,14 +1387,8 @@ static void rcu_torture_timer(struct timer_list *unused) static int rcu_torture_reader(void *arg) { - unsigned long started; - unsigned long completed; - int idx; DEFINE_TORTURE_RANDOM(rand); - struct rcu_torture *p; - int pipe_count; struct timer_list t; - unsigned long long ts; VERBOSE_TOROUT_STRING("rcu_torture_reader task started"); set_user_nice(current, MAX_NICE); @@ -1182,49 +1400,8 @@ rcu_torture_reader(void *arg) if (!timer_pending(&t)) mod_timer(&t, jiffies + 1); } - idx = cur_ops->readlock(); - if (cur_ops->started) - started = cur_ops->started(); - else - started = cur_ops->completed(); - ts = rcu_trace_clock_local(); - p = rcu_dereference_check(rcu_torture_current, - rcu_read_lock_bh_held() || - rcu_read_lock_sched_held() || - srcu_read_lock_held(srcu_ctlp) || - torturing_tasks()); - if (p == NULL) { - /* Wait for rcu_torture_writer to get underway */ - cur_ops->readunlock(idx); + if (!rcu_torture_one_read(&rand)) schedule_timeout_interruptible(HZ); - continue; - } - if (p->rtort_mbtest == 0) - atomic_inc(&n_rcu_torture_mberror); - cur_ops->read_delay(&rand); - preempt_disable(); - pipe_count = p->rtort_pipe_count; - if (pipe_count > RCU_TORTURE_PIPE_LEN) { - /* Should not happen, but... */ - pipe_count = RCU_TORTURE_PIPE_LEN; - } - completed = cur_ops->completed(); - if (pipe_count > 1) { - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, - ts, started, completed); - rcu_ftrace_dump(DUMP_ALL); - } - __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed - started; - if (cur_ops->started) - completed++; - if (completed > RCU_TORTURE_PIPE_LEN) { - /* Should not happen, but... */ - completed = RCU_TORTURE_PIPE_LEN; - } - __this_cpu_inc(rcu_torture_batch[completed]); - preempt_enable(); - cur_ops->readunlock(idx); stutter_wait("rcu_torture_reader"); } while (!torture_must_stop()); if (irqreader && cur_ops->irq_capable) { @@ -1281,7 +1458,7 @@ rcu_torture_stats_print(void) pr_cont("rtbf: %ld rtb: %ld nt: %ld ", n_rcu_torture_boost_failure, n_rcu_torture_boosts, - n_rcu_torture_timers); + atomic_long_read(&n_rcu_torture_timers)); torture_onoff_stats(); pr_cont("barrier: %ld/%ld:%ld ", n_barrier_successes, @@ -1323,18 +1500,16 @@ rcu_torture_stats_print(void) if (rtcv_snap == rcu_torture_current_version && rcu_torture_current != NULL) { int __maybe_unused flags = 0; - unsigned long __maybe_unused gpnum = 0; - unsigned long __maybe_unused completed = 0; + unsigned long __maybe_unused gp_seq = 0; rcutorture_get_gp_data(cur_ops->ttype, - &flags, &gpnum, &completed); + &flags, &gp_seq); srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, - &flags, &gpnum, &completed); + &flags, &gp_seq); wtp = READ_ONCE(writer_task); - pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n", + pr_alert("??? Writer stall state %s(%d) g%lu f%#x ->state %#lx cpu %d\n", rcu_torture_writer_state_getname(), - rcu_torture_writer_state, - gpnum, completed, flags, + rcu_torture_writer_state, gp_seq, flags, wtp == NULL ? ~0UL : wtp->state, wtp == NULL ? -1 : (int)task_cpu(wtp)); if (!splatted && wtp) { @@ -1364,7 +1539,7 @@ rcu_torture_stats(void *arg) return 0; } -static inline void +static void rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) { pr_alert("%s" TORTURE_FLAG @@ -1396,6 +1571,7 @@ static int rcutorture_booster_cleanup(unsigned int cpu) mutex_lock(&boost_mutex); t = boost_tasks[cpu]; boost_tasks[cpu] = NULL; + rcu_torture_enable_rt_throttle(); mutex_unlock(&boost_mutex); /* This must be outside of the mutex, otherwise deadlock! */ @@ -1412,6 +1588,7 @@ static int rcutorture_booster_init(unsigned int cpu) /* Don't allow time recalculation while creating a new task. */ mutex_lock(&boost_mutex); + rcu_torture_disable_rt_throttle(); VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task"); boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL, cpu_to_node(cpu), @@ -1445,7 +1622,7 @@ static int rcu_torture_stall(void *args) VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff"); } if (!kthread_should_stop()) { - stop_at = get_seconds() + stall_cpu; + stop_at = ktime_get_seconds() + stall_cpu; /* RCU CPU stall is expected behavior in following code. */ rcu_read_lock(); if (stall_cpu_irqsoff) @@ -1454,7 +1631,8 @@ static int rcu_torture_stall(void *args) preempt_disable(); pr_alert("rcu_torture_stall start on CPU %d.\n", smp_processor_id()); - while (ULONG_CMP_LT(get_seconds(), stop_at)) + while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(), + stop_at)) continue; /* Induce RCU CPU stall warning. */ if (stall_cpu_irqsoff) local_irq_enable(); @@ -1545,8 +1723,9 @@ static int rcu_torture_barrier(void *arg) atomic_read(&barrier_cbs_invoked), n_barrier_cbs); WARN_ON_ONCE(1); + } else { + n_barrier_successes++; } - n_barrier_successes++; schedule_timeout_interruptible(HZ / 10); } while (!torture_must_stop()); torture_kthread_stopping("rcu_torture_barrier"); @@ -1609,17 +1788,39 @@ static void rcu_torture_barrier_cleanup(void) } } +static bool rcu_torture_can_boost(void) +{ + static int boost_warn_once; + int prio; + + if (!(test_boost == 1 && cur_ops->can_boost) && test_boost != 2) + return false; + + prio = rcu_get_gp_kthreads_prio(); + if (!prio) + return false; + + if (prio < 2) { + if (boost_warn_once == 1) + return false; + + pr_alert("%s: WARN: RCU kthread priority too low to test boosting. Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 on the kernel command line.\n", KBUILD_MODNAME); + boost_warn_once = 1; + return false; + } + + return true; +} + static enum cpuhp_state rcutor_hp; static void rcu_torture_cleanup(void) { int flags = 0; - unsigned long gpnum = 0; - unsigned long completed = 0; + unsigned long gp_seq = 0; int i; - rcutorture_record_test_transition(); if (torture_cleanup_begin()) { if (cur_ops->cb_barrier != NULL) cur_ops->cb_barrier(); @@ -1647,17 +1848,15 @@ rcu_torture_cleanup(void) fakewriter_tasks = NULL; } - rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed); - srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, - &flags, &gpnum, &completed); - pr_alert("%s: End-test grace-period state: g%lu c%lu f%#x\n", - cur_ops->name, gpnum, completed, flags); + rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq); + srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq); + pr_alert("%s: End-test grace-period state: g%lu f%#x\n", + cur_ops->name, gp_seq, flags); torture_stop_kthread(rcu_torture_stats, stats_task); torture_stop_kthread(rcu_torture_fqs, fqs_task); for (i = 0; i < ncbflooders; i++) torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]); - if ((test_boost == 1 && cur_ops->can_boost) || - test_boost == 2) + if (rcu_torture_can_boost()) cpuhp_remove_state(rcutor_hp); /* @@ -1745,7 +1944,7 @@ rcu_torture_init(void) int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, - &sched_ops, &tasks_ops, + &busted_srcud_ops, &sched_ops, &tasks_ops, }; if (!torture_init_begin(torture_type, verbose)) @@ -1762,8 +1961,8 @@ rcu_torture_init(void) torture_type); pr_alert("rcu-torture types:"); for (i = 0; i < ARRAY_SIZE(torture_ops); i++) - pr_alert(" %s", torture_ops[i]->name); - pr_alert("\n"); + pr_cont(" %s", torture_ops[i]->name); + pr_cont("\n"); firsterr = -EINVAL; goto unwind; } @@ -1881,8 +2080,7 @@ rcu_torture_init(void) test_boost_interval = 1; if (test_boost_duration < 2) test_boost_duration = 2; - if ((test_boost == 1 && cur_ops->can_boost) || - test_boost == 2) { + if (rcu_torture_can_boost()) { boost_starttime = jiffies + test_boost_interval * HZ; @@ -1896,7 +2094,7 @@ rcu_torture_init(void) firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup); if (firsterr) goto unwind; - firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ); + firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval); if (firsterr) goto unwind; firsterr = rcu_torture_stall_init(); @@ -1925,7 +2123,6 @@ rcu_torture_init(void) goto unwind; } } - rcutorture_record_test_transition(); torture_init_end(); return 0; diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 622792abe41a..04fc2ed71af8 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -110,7 +110,7 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx) WRITE_ONCE(sp->srcu_lock_nesting[idx], newval); if (!newval && READ_ONCE(sp->srcu_gp_waiting)) - swake_up(&sp->srcu_wq); + swake_up_one(&sp->srcu_wq); } EXPORT_SYMBOL_GPL(__srcu_read_unlock); @@ -140,7 +140,7 @@ void srcu_drive_gp(struct work_struct *wp) idx = sp->srcu_idx; WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx); WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */ - swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); + swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx])); WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */ /* Invoke the callbacks we removed above. */ diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index b4123d7a2cec..6c9866a854b1 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -26,6 +26,8 @@ * */ +#define pr_fmt(fmt) "rcu: " fmt + #include <linux/export.h> #include <linux/mutex.h> #include <linux/percpu.h> @@ -390,7 +392,8 @@ void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced) } if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) || WARN_ON(srcu_readers_active(sp))) { - pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq))); + pr_info("%s: Active srcu_struct %p state: %d\n", + __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq))); return; /* Caller forgot to stop doing call_srcu()? */ } free_percpu(sp->sda); @@ -641,6 +644,9 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp, * period s. Losers must either ensure that their desired grace-period * number is recorded on at least their leaf srcu_node structure, or they * must take steps to invoke their own callbacks. + * + * Note that this function also does the work of srcu_funnel_exp_start(), + * in some cases by directly invoking it. */ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, unsigned long s, bool do_norm) @@ -823,17 +829,17 @@ static void srcu_leak_callback(struct rcu_head *rhp) * more than one CPU, this means that when "func()" is invoked, each CPU * is guaranteed to have executed a full memory barrier since the end of * its last corresponding SRCU read-side critical section whose beginning - * preceded the call to call_rcu(). It also means that each CPU executing + * preceded the call to call_srcu(). It also means that each CPU executing * an SRCU read-side critical section that continues beyond the start of - * "func()" must have executed a memory barrier after the call_rcu() + * "func()" must have executed a memory barrier after the call_srcu() * but before the beginning of that SRCU read-side critical section. * Note that these guarantees include CPUs that are offline, idle, or * executing in user mode, as well as CPUs that are executing in the kernel. * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * Furthermore, if CPU A invoked call_srcu() and CPU B invoked the * resulting SRCU callback function "func()", then both CPU A and CPU * B are guaranteed to execute a full memory barrier during the time - * interval between the call to call_rcu() and the invocation of "func()". + * interval between the call to call_srcu() and the invocation of "func()". * This guarantee applies even if CPU A and CPU B are the same CPU (but * again only if the system has more than one CPU). * @@ -1246,13 +1252,12 @@ static void process_srcu(struct work_struct *work) void srcutorture_get_gp_data(enum rcutorture_type test_type, struct srcu_struct *sp, int *flags, - unsigned long *gpnum, unsigned long *completed) + unsigned long *gp_seq) { if (test_type != SRCU_FLAVOR) return; *flags = 0; - *completed = rcu_seq_ctr(sp->srcu_gp_seq); - *gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed); + *gp_seq = rcu_seq_current(&sp->srcu_gp_seq); } EXPORT_SYMBOL_GPL(srcutorture_get_gp_data); @@ -1263,16 +1268,17 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf) unsigned long s0 = 0, s1 = 0; idx = sp->srcu_idx & 0x1; - pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", tt, tf, idx); + pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):", + tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx); for_each_possible_cpu(cpu) { unsigned long l0, l1; unsigned long u0, u1; long c0, c1; - struct srcu_data *counts; + struct srcu_data *sdp; - counts = per_cpu_ptr(sp->sda, cpu); - u0 = counts->srcu_unlock_count[!idx]; - u1 = counts->srcu_unlock_count[idx]; + sdp = per_cpu_ptr(sp->sda, cpu); + u0 = sdp->srcu_unlock_count[!idx]; + u1 = sdp->srcu_unlock_count[idx]; /* * Make sure that a lock is always counted if the corresponding @@ -1280,12 +1286,13 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf) */ smp_rmb(); - l0 = counts->srcu_lock_count[!idx]; - l1 = counts->srcu_lock_count[idx]; + l0 = sdp->srcu_lock_count[!idx]; + l1 = sdp->srcu_lock_count[idx]; c0 = l0 - u0; c1 = l1 - u1; - pr_cont(" %d(%ld,%ld)", cpu, c0, c1); + pr_cont(" %d(%ld,%ld %1p)", + cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist)); s0 += c0; s1 += c1; } diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index a64eee0db39e..befc9321a89c 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -122,10 +122,8 @@ void rcu_check_callbacks(int user) { if (user) rcu_sched_qs(); - else if (!in_softirq()) + if (user || !in_softirq()) rcu_bh_qs(); - if (user) - rcu_note_voluntary_context_switch(current); } /* diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index aa7cade1b9f3..0b760c1369f7 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -27,6 +27,9 @@ * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU */ + +#define pr_fmt(fmt) "rcu: " fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -95,13 +98,13 @@ struct rcu_state sname##_state = { \ .rda = &sname##_data, \ .call = cr, \ .gp_state = RCU_GP_IDLE, \ - .gpnum = 0UL - 300UL, \ - .completed = 0UL - 300UL, \ + .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ .exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \ .exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \ + .ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \ } RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); @@ -155,6 +158,9 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active); */ static int rcu_scheduler_fully_active __read_mostly; +static void +rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long gps, unsigned long flags); static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); @@ -177,6 +183,13 @@ module_param(gp_init_delay, int, 0444); static int gp_cleanup_delay; module_param(gp_cleanup_delay, int, 0444); +/* Retreive RCU kthreads priority for rcutorture */ +int rcu_get_gp_kthreads_prio(void) +{ + return kthread_prio; +} +EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio); + /* * Number of grace periods between delays, normalized by the duration of * the delay. The longer the delay, the more the grace periods between @@ -189,18 +202,6 @@ module_param(gp_cleanup_delay, int, 0444); #define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */ /* - * Track the rcutorture test sequence number and the update version - * number within a given test. The rcutorture_testseq is incremented - * on every rcutorture module load and unload, so has an odd value - * when a test is running. The rcutorture_vernum is set to zero - * when rcutorture starts and is incremented on each rcutorture update. - * These variables enable correlating rcutorture output with the - * RCU tracing information. - */ -unsigned long rcutorture_testseq; -unsigned long rcutorture_vernum; - -/* * Compute the mask of online CPUs for the specified rcu_node structure. * This will not be stable unless the rcu_node structure's ->lock is * held, but the bit corresponding to the current CPU will be stable @@ -218,7 +219,7 @@ unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) */ static int rcu_gp_in_progress(struct rcu_state *rsp) { - return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum); + return rcu_seq_state(rcu_seq_current(&rsp->gp_seq)); } /* @@ -233,7 +234,7 @@ void rcu_sched_qs(void) if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) return; trace_rcu_grace_period(TPS("rcu_sched"), - __this_cpu_read(rcu_sched_data.gpnum), + __this_cpu_read(rcu_sched_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) @@ -248,7 +249,7 @@ void rcu_bh_qs(void) RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_bh"), - __this_cpu_read(rcu_bh_data.gpnum), + __this_cpu_read(rcu_bh_data.gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); } @@ -380,20 +381,6 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap) } /* - * Do a double-increment of the ->dynticks counter to emulate a - * momentary idle-CPU quiescent state. - */ -static void rcu_dynticks_momentary_idle(void) -{ - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, - &rdtp->dynticks); - - /* It is illegal to call this from idle state. */ - WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); -} - -/* * Set the special (bottom) bit of the specified CPU so that it * will take special action (such as flushing its TLB) on the * next exit from an extended quiescent state. Returns true if @@ -424,12 +411,17 @@ bool rcu_eqs_special_set(int cpu) * * We inform the RCU core by emulating a zero-duration dyntick-idle period. * - * The caller must have disabled interrupts. + * The caller must have disabled interrupts and must not be idle. */ static void rcu_momentary_dyntick_idle(void) { + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + int special; + raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false); - rcu_dynticks_momentary_idle(); + special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); + /* It is illegal to call this from idle state. */ + WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); } /* @@ -451,7 +443,7 @@ void rcu_note_context_switch(bool preempt) rcu_momentary_dyntick_idle(); this_cpu_inc(rcu_dynticks.rcu_qs_ctr); if (!preempt) - rcu_note_voluntary_context_switch_lite(current); + rcu_tasks_qs(current); out: trace_rcu_utilization(TPS("End context switch")); barrier(); /* Avoid RCU read-side critical sections leaking up. */ @@ -513,8 +505,38 @@ static ulong jiffies_till_first_fqs = ULONG_MAX; static ulong jiffies_till_next_fqs = ULONG_MAX; static bool rcu_kick_kthreads; -module_param(jiffies_till_first_fqs, ulong, 0644); -module_param(jiffies_till_next_fqs, ulong, 0644); +static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp) +{ + ulong j; + int ret = kstrtoul(val, 0, &j); + + if (!ret) + WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j); + return ret; +} + +static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp) +{ + ulong j; + int ret = kstrtoul(val, 0, &j); + + if (!ret) + WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1)); + return ret; +} + +static struct kernel_param_ops first_fqs_jiffies_ops = { + .set = param_set_first_fqs_jiffies, + .get = param_get_ulong, +}; + +static struct kernel_param_ops next_fqs_jiffies_ops = { + .set = param_set_next_fqs_jiffies, + .get = param_get_ulong, +}; + +module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644); +module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644); module_param(rcu_kick_kthreads, bool, 0644); /* @@ -529,58 +551,31 @@ static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(void); /* - * Return the number of RCU batches started thus far for debug & stats. + * Return the number of RCU GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_started(void) +unsigned long rcu_get_gp_seq(void) { - return rcu_state_p->gpnum; + return READ_ONCE(rcu_state_p->gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_started); +EXPORT_SYMBOL_GPL(rcu_get_gp_seq); /* - * Return the number of RCU-sched batches started thus far for debug & stats. + * Return the number of RCU-sched GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_started_sched(void) +unsigned long rcu_sched_get_gp_seq(void) { - return rcu_sched_state.gpnum; + return READ_ONCE(rcu_sched_state.gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_started_sched); +EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq); /* - * Return the number of RCU BH batches started thus far for debug & stats. + * Return the number of RCU-bh GPs completed thus far for debug & stats. */ -unsigned long rcu_batches_started_bh(void) +unsigned long rcu_bh_get_gp_seq(void) { - return rcu_bh_state.gpnum; + return READ_ONCE(rcu_bh_state.gp_seq); } -EXPORT_SYMBOL_GPL(rcu_batches_started_bh); - -/* - * Return the number of RCU batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed(void) -{ - return rcu_state_p->completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed); - -/* - * Return the number of RCU-sched batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed_sched(void) -{ - return rcu_sched_state.completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); - -/* - * Return the number of RCU BH batches completed thus far for debug & stats. - */ -unsigned long rcu_batches_completed_bh(void) -{ - return rcu_bh_state.completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); +EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq); /* * Return the number of RCU expedited batches completed thus far for @@ -636,35 +631,42 @@ EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); */ void show_rcu_gp_kthreads(void) { + int cpu; + struct rcu_data *rdp; + struct rcu_node *rnp; struct rcu_state *rsp; for_each_rcu_flavor(rsp) { pr_info("%s: wait state: %d ->state: %#lx\n", rsp->name, rsp->gp_state, rsp->gp_kthread->state); + rcu_for_each_node_breadth_first(rsp, rnp) { + if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed)) + continue; + pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n", + rnp->grplo, rnp->grphi, rnp->gp_seq, + rnp->gp_seq_needed); + if (!rcu_is_leaf_node(rnp)) + continue; + for_each_leaf_node_possible_cpu(rnp, cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + if (rdp->gpwrap || + ULONG_CMP_GE(rsp->gp_seq, + rdp->gp_seq_needed)) + continue; + pr_info("\tcpu %d ->gp_seq_needed %lu\n", + cpu, rdp->gp_seq_needed); + } + } /* sched_show_task(rsp->gp_kthread); */ } } EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); /* - * Record the number of times rcutorture tests have been initiated and - * terminated. This information allows the debugfs tracing stats to be - * correlated to the rcutorture messages, even when the rcutorture module - * is being repeatedly loaded and unloaded. In other words, we cannot - * store this state in rcutorture itself. - */ -void rcutorture_record_test_transition(void) -{ - rcutorture_testseq++; - rcutorture_vernum = 0; -} -EXPORT_SYMBOL_GPL(rcutorture_record_test_transition); - -/* * Send along grace-period-related data for rcutorture diagnostics. */ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, - unsigned long *gpnum, unsigned long *completed) + unsigned long *gp_seq) { struct rcu_state *rsp = NULL; @@ -684,23 +686,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, if (rsp == NULL) return; *flags = READ_ONCE(rsp->gp_flags); - *gpnum = READ_ONCE(rsp->gpnum); - *completed = READ_ONCE(rsp->completed); + *gp_seq = rcu_seq_current(&rsp->gp_seq); } EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); /* - * Record the number of writer passes through the current rcutorture test. - * This is also used to correlate debugfs tracing stats with the rcutorture - * messages. - */ -void rcutorture_record_progress(unsigned long vernum) -{ - rcutorture_vernum++; -} -EXPORT_SYMBOL_GPL(rcutorture_record_progress); - -/* * Return the root node of the specified rcu_state structure. */ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) @@ -1059,41 +1049,41 @@ void rcu_request_urgent_qs_task(struct task_struct *t) #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* - * Is the current CPU online? Disable preemption to avoid false positives - * that could otherwise happen due to the current CPU number being sampled, - * this task being preempted, its old CPU being taken offline, resuming - * on some other CPU, then determining that its old CPU is now offline. - * It is OK to use RCU on an offline processor during initial boot, hence - * the check for rcu_scheduler_fully_active. Note also that it is OK - * for a CPU coming online to use RCU for one jiffy prior to marking itself - * online in the cpu_online_mask. Similarly, it is OK for a CPU going - * offline to continue to use RCU for one jiffy after marking itself - * offline in the cpu_online_mask. This leniency is necessary given the - * non-atomic nature of the online and offline processing, for example, - * the fact that a CPU enters the scheduler after completing the teardown - * of the CPU. + * Is the current CPU online as far as RCU is concerned? * - * This is also why RCU internally marks CPUs online during in the - * preparation phase and offline after the CPU has been taken down. + * Disable preemption to avoid false positives that could otherwise + * happen due to the current CPU number being sampled, this task being + * preempted, its old CPU being taken offline, resuming on some other CPU, + * then determining that its old CPU is now offline. Because there are + * multiple flavors of RCU, and because this function can be called in the + * midst of updating the flavors while a given CPU coming online or going + * offline, it is necessary to check all flavors. If any of the flavors + * believe that given CPU is online, it is considered to be online. * - * Disable checking if in an NMI handler because we cannot safely report - * errors from NMI handlers anyway. + * Disable checking if in an NMI handler because we cannot safely + * report errors from NMI handlers anyway. In addition, it is OK to use + * RCU on an offline processor during initial boot, hence the check for + * rcu_scheduler_fully_active. */ bool rcu_lockdep_current_cpu_online(void) { struct rcu_data *rdp; struct rcu_node *rnp; - bool ret; + struct rcu_state *rsp; - if (in_nmi()) + if (in_nmi() || !rcu_scheduler_fully_active) return true; preempt_disable(); - rdp = this_cpu_ptr(&rcu_sched_data); - rnp = rdp->mynode; - ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) || - !rcu_scheduler_fully_active; + for_each_rcu_flavor(rsp) { + rdp = this_cpu_ptr(rsp->rda); + rnp = rdp->mynode; + if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) { + preempt_enable(); + return true; + } + } preempt_enable(); - return ret; + return false; } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); @@ -1115,17 +1105,18 @@ static int rcu_is_cpu_rrupt_from_idle(void) /* * We are reporting a quiescent state on behalf of some other CPU, so * it is our responsibility to check for and handle potential overflow - * of the rcu_node ->gpnum counter with respect to the rcu_data counters. + * of the rcu_node ->gp_seq counter with respect to the rcu_data counters. * After all, the CPU might be in deep idle state, and thus executing no * code whatsoever. */ static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp) { raw_lockdep_assert_held_rcu_node(rnp); - if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum)) + if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4, + rnp->gp_seq)) WRITE_ONCE(rdp->gpwrap, true); - if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum)) - rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4; + if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq)) + rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4; } /* @@ -1137,7 +1128,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) { rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); rcu_gpnum_ovf(rdp->mynode, rdp); return 1; } @@ -1159,7 +1150,7 @@ static void rcu_iw_handler(struct irq_work *iwp) rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) { - rdp->rcu_iw_gpnum = rnp->gpnum; + rdp->rcu_iw_gp_seq = rnp->gp_seq; rdp->rcu_iw_pending = false; } raw_spin_unlock_rcu_node(rnp); @@ -1187,7 +1178,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * of the current RCU grace period. */ if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); rdp->dynticks_fqs++; rcu_gpnum_ovf(rnp, rdp); return 1; @@ -1203,8 +1194,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu); if (time_after(jiffies, rdp->rsp->gp_start + jtsq) && READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) && - READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc")); + rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) { + trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc")); rcu_gpnum_ovf(rnp, rdp); return 1; } else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) { @@ -1212,12 +1203,25 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) smp_store_release(ruqp, true); } - /* Check for the CPU being offline. */ - if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl")); - rdp->offline_fqs++; - rcu_gpnum_ovf(rnp, rdp); - return 1; + /* If waiting too long on an offline CPU, complain. */ + if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) && + time_after(jiffies, rdp->rsp->gp_start + HZ)) { + bool onl; + struct rcu_node *rnp1; + + WARN_ON(1); /* Offline CPUs are supposed to report QS! */ + pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n", + __func__, rnp->grplo, rnp->grphi, rnp->level, + (long)rnp->gp_seq, (long)rnp->completedqs); + for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent) + pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n", + __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask); + onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); + pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n", + __func__, rdp->cpu, ".o"[onl], + (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, + (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); + return 1; /* Break things loose after complaining. */ } /* @@ -1256,11 +1260,11 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) { resched_cpu(rdp->cpu); if (IS_ENABLED(CONFIG_IRQ_WORK) && - !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum && + !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq && (rnp->ffmask & rdp->grpmask)) { init_irq_work(&rdp->rcu_iw, rcu_iw_handler); rdp->rcu_iw_pending = true; - rdp->rcu_iw_gpnum = rnp->gpnum; + rdp->rcu_iw_gp_seq = rnp->gp_seq; irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); } } @@ -1274,9 +1278,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) unsigned long j1; rsp->gp_start = j; - smp_wmb(); /* Record start time before stall time. */ j1 = rcu_jiffies_till_stall_check(); - WRITE_ONCE(rsp->jiffies_stall, j + j1); + /* Record ->gp_start before ->jiffies_stall. */ + smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */ rsp->jiffies_resched = j + j1 / 2; rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs); } @@ -1302,9 +1306,9 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) j = jiffies; gpa = READ_ONCE(rsp->gp_activity); if (j - gpa > 2 * HZ) { - pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n", + pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n", rsp->name, j - gpa, - rsp->gpnum, rsp->completed, + (long)rcu_seq_current(&rsp->gp_seq), rsp->gp_flags, gp_state_getname(rsp->gp_state), rsp->gp_state, rsp->gp_kthread ? rsp->gp_kthread->state : ~0, @@ -1359,16 +1363,15 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp) } } -static inline void panic_on_rcu_stall(void) +static void panic_on_rcu_stall(void) { if (sysctl_panic_on_rcu_stall) panic("RCU Stall\n"); } -static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) +static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq) { int cpu; - long delta; unsigned long flags; unsigned long gpa; unsigned long j; @@ -1381,25 +1384,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) if (rcu_cpu_stall_suppress) return; - /* Only let one CPU complain about others per time interval. */ - - raw_spin_lock_irqsave_rcu_node(rnp, flags); - delta = jiffies - READ_ONCE(rsp->jiffies_stall); - if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - return; - } - WRITE_ONCE(rsp->jiffies_stall, - jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - /* * OK, time to rat on our buddy... * See Documentation/RCU/stallwarn.txt for info on how to debug * RCU CPU stall warnings. */ - pr_err("INFO: %s detected stalls on CPUs/tasks:", - rsp->name); + pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name); print_cpu_stall_info_begin(); rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -1418,17 +1408,16 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) for_each_possible_cpu(cpu) totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, cpu)->cblist); - pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n", + pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n", smp_processor_id(), (long)(jiffies - rsp->gp_start), - (long)rsp->gpnum, (long)rsp->completed, totqlen); + (long)rcu_seq_current(&rsp->gp_seq), totqlen); if (ndetected) { rcu_dump_cpu_stacks(rsp); /* Complain about tasks blocking the grace period. */ rcu_print_detail_task_stall(rsp); } else { - if (READ_ONCE(rsp->gpnum) != gpnum || - READ_ONCE(rsp->completed) == gpnum) { + if (rcu_seq_current(&rsp->gp_seq) != gp_seq) { pr_err("INFO: Stall ended before state dump start\n"); } else { j = jiffies; @@ -1441,6 +1430,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) sched_show_task(current); } } + /* Rewrite if needed in case of slow consoles. */ + if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) + WRITE_ONCE(rsp->jiffies_stall, + jiffies + 3 * rcu_jiffies_till_stall_check() + 3); rcu_check_gp_kthread_starvation(rsp); @@ -1476,15 +1469,16 @@ static void print_cpu_stall(struct rcu_state *rsp) for_each_possible_cpu(cpu) totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, cpu)->cblist); - pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n", + pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n", jiffies - rsp->gp_start, - (long)rsp->gpnum, (long)rsp->completed, totqlen); + (long)rcu_seq_current(&rsp->gp_seq), totqlen); rcu_check_gp_kthread_starvation(rsp); rcu_dump_cpu_stacks(rsp); raw_spin_lock_irqsave_rcu_node(rnp, flags); + /* Rewrite if needed in case of slow consoles. */ if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) WRITE_ONCE(rsp->jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); @@ -1504,10 +1498,11 @@ static void print_cpu_stall(struct rcu_state *rsp) static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) { - unsigned long completed; - unsigned long gpnum; + unsigned long gs1; + unsigned long gs2; unsigned long gps; unsigned long j; + unsigned long jn; unsigned long js; struct rcu_node *rnp; @@ -1520,43 +1515,46 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) /* * Lots of memory barriers to reject false positives. * - * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall, - * then rsp->gp_start, and finally rsp->completed. These values - * are updated in the opposite order with memory barriers (or - * equivalent) during grace-period initialization and cleanup. - * Now, a false positive can occur if we get an new value of - * rsp->gp_start and a old value of rsp->jiffies_stall. But given - * the memory barriers, the only way that this can happen is if one - * grace period ends and another starts between these two fetches. - * Detect this by comparing rsp->completed with the previous fetch - * from rsp->gpnum. + * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall, + * then rsp->gp_start, and finally another copy of rsp->gp_seq. + * These values are updated in the opposite order with memory + * barriers (or equivalent) during grace-period initialization + * and cleanup. Now, a false positive can occur if we get an new + * value of rsp->gp_start and a old value of rsp->jiffies_stall. + * But given the memory barriers, the only way that this can happen + * is if one grace period ends and another starts between these + * two fetches. This is detected by comparing the second fetch + * of rsp->gp_seq with the previous fetch from rsp->gp_seq. * * Given this check, comparisons of jiffies, rsp->jiffies_stall, * and rsp->gp_start suffice to forestall false positives. */ - gpnum = READ_ONCE(rsp->gpnum); - smp_rmb(); /* Pick up ->gpnum first... */ + gs1 = READ_ONCE(rsp->gp_seq); + smp_rmb(); /* Pick up ->gp_seq first... */ js = READ_ONCE(rsp->jiffies_stall); smp_rmb(); /* ...then ->jiffies_stall before the rest... */ gps = READ_ONCE(rsp->gp_start); - smp_rmb(); /* ...and finally ->gp_start before ->completed. */ - completed = READ_ONCE(rsp->completed); - if (ULONG_CMP_GE(completed, gpnum) || + smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */ + gs2 = READ_ONCE(rsp->gp_seq); + if (gs1 != gs2 || ULONG_CMP_LT(j, js) || ULONG_CMP_GE(gps, js)) return; /* No stall or GP completed since entering function. */ rnp = rdp->mynode; + jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; if (rcu_gp_in_progress(rsp) && - (READ_ONCE(rnp->qsmask) & rdp->grpmask)) { + (READ_ONCE(rnp->qsmask) & rdp->grpmask) && + cmpxchg(&rsp->jiffies_stall, js, jn) == js) { /* We haven't checked in, so go dump stack. */ print_cpu_stall(rsp); } else if (rcu_gp_in_progress(rsp) && - ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) { + ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) && + cmpxchg(&rsp->jiffies_stall, js, jn) == js) { /* They had a few time units to dump stack, so complain. */ - print_other_cpu_stall(rsp, gpnum); + print_other_cpu_stall(rsp, gs2); } } @@ -1577,123 +1575,99 @@ void rcu_cpu_stall_reset(void) WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2); } -/* - * Determine the value that ->completed will have at the end of the - * next subsequent grace period. This is used to tag callbacks so that - * a CPU can invoke callbacks in a timely fashion even if that CPU has - * been dyntick-idle for an extended period with callbacks under the - * influence of RCU_FAST_NO_HZ. - * - * The caller must hold rnp->lock with interrupts disabled. - */ -static unsigned long rcu_cbs_completed(struct rcu_state *rsp, - struct rcu_node *rnp) -{ - raw_lockdep_assert_held_rcu_node(rnp); - - /* - * If RCU is idle, we just wait for the next grace period. - * But we can only be sure that RCU is idle if we are looking - * at the root rcu_node structure -- otherwise, a new grace - * period might have started, but just not yet gotten around - * to initializing the current non-root rcu_node structure. - */ - if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed) - return rnp->completed + 1; - - /* - * If the current rcu_node structure believes that RCU is - * idle, and if the rcu_state structure does not yet reflect - * the start of a new grace period, then the next grace period - * will suffice. The memory barrier is needed to accurately - * sample the rsp->gpnum, and pairs with the second lock - * acquisition in rcu_gp_init(), which is augmented with - * smp_mb__after_unlock_lock() for this purpose. - */ - if (rnp->gpnum == rnp->completed) { - smp_mb(); /* See above block comment. */ - if (READ_ONCE(rsp->gpnum) == rnp->completed) - return rnp->completed + 1; - } - - /* - * Otherwise, wait for a possible partial grace period and - * then the subsequent full grace period. - */ - return rnp->completed + 2; -} - /* Trace-event wrapper function for trace_rcu_future_grace_period. */ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c, const char *s) + unsigned long gp_seq_req, const char *s) { - trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum, - rnp->completed, c, rnp->level, - rnp->grplo, rnp->grphi, s); + trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req, + rnp->level, rnp->grplo, rnp->grphi, s); } /* + * rcu_start_this_gp - Request the start of a particular grace period + * @rnp_start: The leaf node of the CPU from which to start. + * @rdp: The rcu_data corresponding to the CPU from which to start. + * @gp_seq_req: The gp_seq of the grace period to start. + * * Start the specified grace period, as needed to handle newly arrived * callbacks. The required future grace periods are recorded in each - * rcu_node structure's ->need_future_gp[] field. Returns true if there + * rcu_node structure's ->gp_seq_needed field. Returns true if there * is reason to awaken the grace-period kthread. * * The caller must hold the specified rcu_node structure's ->lock, which * is why the caller is responsible for waking the grace-period kthread. + * + * Returns true if the GP thread needs to be awakened else false. */ -static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long c) +static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp, + unsigned long gp_seq_req) { bool ret = false; struct rcu_state *rsp = rdp->rsp; - struct rcu_node *rnp_root; + struct rcu_node *rnp; /* * Use funnel locking to either acquire the root rcu_node * structure's lock or bail out if the need for this grace period - * has already been recorded -- or has already started. If there - * is already a grace period in progress in a non-leaf node, no - * recording is needed because the end of the grace period will - * scan the leaf rcu_node structures. Note that rnp->lock must - * not be released. + * has already been recorded -- or if that grace period has in + * fact already started. If there is already a grace period in + * progress in a non-leaf node, no recording is needed because the + * end of the grace period will scan the leaf rcu_node structures. + * Note that rnp_start->lock must not be released. */ - raw_lockdep_assert_held_rcu_node(rnp); - trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf")); - for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) { - if (rnp_root != rnp) - raw_spin_lock_rcu_node(rnp_root); - WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum + - need_future_gp_mask(), c)); - if (need_future_gp_element(rnp_root, c) || - ULONG_CMP_GE(rnp_root->gpnum, c) || - (rnp != rnp_root && - rnp_root->gpnum != rnp_root->completed)) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted")); + raw_lockdep_assert_held_rcu_node(rnp_start); + trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf")); + for (rnp = rnp_start; 1; rnp = rnp->parent) { + if (rnp != rnp_start) + raw_spin_lock_rcu_node(rnp); + if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) || + rcu_seq_started(&rnp->gp_seq, gp_seq_req) || + (rnp != rnp_start && + rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) { + trace_rcu_this_gp(rnp, rdp, gp_seq_req, + TPS("Prestarted")); goto unlock_out; } - need_future_gp_element(rnp_root, c) = true; - if (rnp_root != rnp && rnp_root->parent != NULL) - raw_spin_unlock_rcu_node(rnp_root); - if (!rnp_root->parent) + rnp->gp_seq_needed = gp_seq_req; + if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) { + /* + * We just marked the leaf or internal node, and a + * grace period is in progress, which means that + * rcu_gp_cleanup() will see the marking. Bail to + * reduce contention. + */ + trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, + TPS("Startedleaf")); + goto unlock_out; + } + if (rnp != rnp_start && rnp->parent != NULL) + raw_spin_unlock_rcu_node(rnp); + if (!rnp->parent) break; /* At root, and perhaps also leaf. */ } /* If GP already in progress, just leave, otherwise start one. */ - if (rnp_root->gpnum != rnp_root->completed) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot")); + if (rcu_gp_in_progress(rsp)) { + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot")); goto unlock_out; } - trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot")); + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot")); WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT); + rsp->gp_req_activity = jiffies; if (!rsp->gp_kthread) { - trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread")); + trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread")); goto unlock_out; } - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq")); + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); ret = true; /* Caller must wake GP kthread. */ unlock_out: - if (rnp != rnp_root) - raw_spin_unlock_rcu_node(rnp_root); + /* Push furthest requested GP to leaf node and rcu_data structure. */ + if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) { + rnp_start->gp_seq_needed = rnp->gp_seq_needed; + rdp->gp_seq_needed = rnp->gp_seq_needed; + } + if (rnp != rnp_start) + raw_spin_unlock_rcu_node(rnp); return ret; } @@ -1703,13 +1677,13 @@ unlock_out: */ static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { - unsigned long c = rnp->completed; bool needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - need_future_gp_element(rnp, c) = false; - needmore = need_any_future_gp(rnp); - trace_rcu_this_gp(rnp, rdp, c, + needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed); + if (!needmore) + rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */ + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq, needmore ? TPS("CleanupMore") : TPS("Cleanup")); return needmore; } @@ -1727,25 +1701,25 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; - swake_up(&rsp->gp_wq); + swake_up_one(&rsp->gp_wq); } /* - * If there is room, assign a ->completed number to any callbacks on - * this CPU that have not already been assigned. Also accelerate any - * callbacks that were previously assigned a ->completed number that has - * since proven to be too conservative, which can happen if callbacks get - * assigned a ->completed number while RCU is idle, but with reference to - * a non-root rcu_node structure. This function is idempotent, so it does - * not hurt to call it repeatedly. Returns an flag saying that we should - * awaken the RCU grace-period kthread. + * If there is room, assign a ->gp_seq number to any callbacks on this + * CPU that have not already been assigned. Also accelerate any callbacks + * that were previously assigned a ->gp_seq number that has since proven + * to be too conservative, which can happen if callbacks get assigned a + * ->gp_seq number while RCU is idle, but with reference to a non-root + * rcu_node structure. This function is idempotent, so it does not hurt + * to call it repeatedly. Returns an flag saying that we should awaken + * the RCU grace-period kthread. * * The caller must hold rnp->lock with interrupts disabled. */ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - unsigned long c; + unsigned long gp_seq_req; bool ret = false; raw_lockdep_assert_held_rcu_node(rnp); @@ -1764,22 +1738,50 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * accelerating callback invocation to an earlier grace-period * number. */ - c = rcu_cbs_completed(rsp, rnp); - if (rcu_segcblist_accelerate(&rdp->cblist, c)) - ret = rcu_start_this_gp(rnp, rdp, c); + gp_seq_req = rcu_seq_snap(&rsp->gp_seq); + if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req)) + ret = rcu_start_this_gp(rnp, rdp, gp_seq_req); /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB")); else - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB")); + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB")); return ret; } /* + * Similar to rcu_accelerate_cbs(), but does not require that the leaf + * rcu_node structure's ->lock be held. It consults the cached value + * of ->gp_seq_needed in the rcu_data structure, and if that indicates + * that a new grace-period request be made, invokes rcu_accelerate_cbs() + * while holding the leaf rcu_node structure's ->lock. + */ +static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp, + struct rcu_node *rnp, + struct rcu_data *rdp) +{ + unsigned long c; + bool needwake; + + lockdep_assert_irqs_disabled(); + c = rcu_seq_snap(&rsp->gp_seq); + if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { + /* Old request still live, so mark recent callbacks. */ + (void)rcu_segcblist_accelerate(&rdp->cblist, c); + return; + } + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ + if (needwake) + rcu_gp_kthread_wake(rsp); +} + +/* * Move any callbacks whose grace period has completed to the * RCU_DONE_TAIL sublist, then compact the remaining sublists and - * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL + * assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL * sublist. This function is idempotent, so it does not hurt to * invoke it repeatedly. As long as it is not invoked -too- often... * Returns true if the RCU grace-period kthread needs to be awakened. @@ -1796,10 +1798,10 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, return false; /* - * Find all callbacks whose ->completed numbers indicate that they + * Find all callbacks whose ->gp_seq numbers indicate that they * are ready to invoke, and put them into the RCU_DONE_TAIL sublist. */ - rcu_segcblist_advance(&rdp->cblist, rnp->completed); + rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq); /* Classify any remaining callbacks. */ return rcu_accelerate_cbs(rsp, rnp, rdp); @@ -1819,39 +1821,38 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, raw_lockdep_assert_held_rcu_node(rnp); - /* Handle the ends of any preceding grace periods first. */ - if (rdp->completed == rnp->completed && - !unlikely(READ_ONCE(rdp->gpwrap))) { - - /* No grace period end, so just accelerate recent callbacks. */ - ret = rcu_accelerate_cbs(rsp, rnp, rdp); + if (rdp->gp_seq == rnp->gp_seq) + return false; /* Nothing to do. */ + /* Handle the ends of any preceding grace periods first. */ + if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) || + unlikely(READ_ONCE(rdp->gpwrap))) { + ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */ + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend")); } else { - - /* Advance callbacks. */ - ret = rcu_advance_cbs(rsp, rnp, rdp); - - /* Remember that we saw this grace-period completion. */ - rdp->completed = rnp->completed; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend")); + ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */ } - if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) { + /* Now handle the beginnings of any new-to-this-CPU grace periods. */ + if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) || + unlikely(READ_ONCE(rdp->gpwrap))) { /* * If the current grace period is waiting for this CPU, * set up to detect a quiescent state, otherwise don't * go looking for one. */ - rdp->gpnum = rnp->gpnum; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); + trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart")); need_gp = !!(rnp->qsmask & rdp->grpmask); rdp->cpu_no_qs.b.norm = need_gp; rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr); rdp->core_needs_qs = need_gp; zero_cpu_stall_ticks(rdp); - WRITE_ONCE(rdp->gpwrap, false); - rcu_gpnum_ovf(rnp, rdp); } + rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */ + if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap) + rdp->gp_seq_needed = rnp->gp_seq_needed; + WRITE_ONCE(rdp->gpwrap, false); + rcu_gpnum_ovf(rnp, rdp); return ret; } @@ -1863,8 +1864,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_save(flags); rnp = rdp->mynode; - if ((rdp->gpnum == READ_ONCE(rnp->gpnum) && - rdp->completed == READ_ONCE(rnp->completed) && + if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) && !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */ !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */ local_irq_restore(flags); @@ -1879,7 +1879,8 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) static void rcu_gp_slow(struct rcu_state *rsp, int delay) { if (delay > 0 && - !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) + !(rcu_seq_ctr(rsp->gp_seq) % + (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) schedule_timeout_uninterruptible(delay); } @@ -1888,7 +1889,9 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay) */ static bool rcu_gp_init(struct rcu_state *rsp) { + unsigned long flags; unsigned long oldmask; + unsigned long mask; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); @@ -1912,9 +1915,9 @@ static bool rcu_gp_init(struct rcu_state *rsp) /* Advance to a new grace period and initialize state. */ record_gp_stall_check_time(rsp); - /* Record GP times before starting GP, hence smp_store_release(). */ - smp_store_release(&rsp->gpnum, rsp->gpnum + 1); - trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); + /* Record GP times before starting GP, hence rcu_seq_start(). */ + rcu_seq_start(&rsp->gp_seq); + trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start")); raw_spin_unlock_irq_rcu_node(rnp); /* @@ -1923,13 +1926,15 @@ static bool rcu_gp_init(struct rcu_state *rsp) * for subsequent online CPUs, and that quiescent-state forcing * will handle subsequent offline CPUs. */ + rsp->gp_state = RCU_GP_ONOFF; rcu_for_each_leaf_node(rsp, rnp) { - rcu_gp_slow(rsp, gp_preinit_delay); + spin_lock(&rsp->ofl_lock); raw_spin_lock_irq_rcu_node(rnp); if (rnp->qsmaskinit == rnp->qsmaskinitnext && !rnp->wait_blkd_tasks) { /* Nothing to do on this leaf rcu_node structure. */ raw_spin_unlock_irq_rcu_node(rnp); + spin_unlock(&rsp->ofl_lock); continue; } @@ -1939,12 +1944,14 @@ static bool rcu_gp_init(struct rcu_state *rsp) /* If zero-ness of ->qsmaskinit changed, propagate up tree. */ if (!oldmask != !rnp->qsmaskinit) { - if (!oldmask) /* First online CPU for this rcu_node. */ - rcu_init_new_rnp(rnp); - else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */ - rnp->wait_blkd_tasks = true; - else /* Last offline CPU and can propagate. */ + if (!oldmask) { /* First online CPU for rcu_node. */ + if (!rnp->wait_blkd_tasks) /* Ever offline? */ + rcu_init_new_rnp(rnp); + } else if (rcu_preempt_has_tasks(rnp)) { + rnp->wait_blkd_tasks = true; /* blocked tasks */ + } else { /* Last offline CPU and can propagate. */ rcu_cleanup_dead_rnp(rnp); + } } /* @@ -1953,18 +1960,19 @@ static bool rcu_gp_init(struct rcu_state *rsp) * still offline, propagate up the rcu_node tree and * clear ->wait_blkd_tasks. Otherwise, if one of this * rcu_node structure's CPUs has since come back online, - * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp() - * checks for this, so just call it unconditionally). + * simply clear ->wait_blkd_tasks. */ if (rnp->wait_blkd_tasks && - (!rcu_preempt_has_tasks(rnp) || - rnp->qsmaskinit)) { + (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) { rnp->wait_blkd_tasks = false; - rcu_cleanup_dead_rnp(rnp); + if (!rnp->qsmaskinit) + rcu_cleanup_dead_rnp(rnp); } raw_spin_unlock_irq_rcu_node(rnp); + spin_unlock(&rsp->ofl_lock); } + rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */ /* * Set the quiescent-state-needed bits in all the rcu_node @@ -1978,22 +1986,27 @@ static bool rcu_gp_init(struct rcu_state *rsp) * The grace period cannot complete until the initialization * process finishes, because this kthread handles both. */ + rsp->gp_state = RCU_GP_INIT; rcu_for_each_node_breadth_first(rsp, rnp) { rcu_gp_slow(rsp, gp_init_delay); - raw_spin_lock_irq_rcu_node(rnp); + raw_spin_lock_irqsave_rcu_node(rnp, flags); rdp = this_cpu_ptr(rsp->rda); - rcu_preempt_check_blocked_tasks(rnp); + rcu_preempt_check_blocked_tasks(rsp, rnp); rnp->qsmask = rnp->qsmaskinit; - WRITE_ONCE(rnp->gpnum, rsp->gpnum); - if (WARN_ON_ONCE(rnp->completed != rsp->completed)) - WRITE_ONCE(rnp->completed, rsp->completed); + WRITE_ONCE(rnp->gp_seq, rsp->gp_seq); if (rnp == rdp->mynode) (void)__note_gp_changes(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); - trace_rcu_grace_period_init(rsp->name, rnp->gpnum, + trace_rcu_grace_period_init(rsp->name, rnp->gp_seq, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); - raw_spin_unlock_irq_rcu_node(rnp); + /* Quiescent states for tasks on any now-offline CPUs. */ + mask = rnp->qsmask & ~rnp->qsmaskinitnext; + rnp->rcu_gp_init_mask = mask; + if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp)) + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + else + raw_spin_unlock_irq_rcu_node(rnp); cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); } @@ -2002,7 +2015,7 @@ static bool rcu_gp_init(struct rcu_state *rsp) } /* - * Helper function for swait_event_idle() wakeup at force-quiescent-state + * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state * time. */ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) @@ -2053,6 +2066,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) { unsigned long gp_duration; bool needgp = false; + unsigned long new_gp_seq; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); struct swait_queue_head *sq; @@ -2074,19 +2088,22 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) raw_spin_unlock_irq_rcu_node(rnp); /* - * Propagate new ->completed value to rcu_node structures so - * that other CPUs don't have to wait until the start of the next - * grace period to process their callbacks. This also avoids - * some nasty RCU grace-period initialization races by forcing - * the end of the current grace period to be completely recorded in - * all of the rcu_node structures before the beginning of the next - * grace period is recorded in any of the rcu_node structures. + * Propagate new ->gp_seq value to rcu_node structures so that + * other CPUs don't have to wait until the start of the next grace + * period to process their callbacks. This also avoids some nasty + * RCU grace-period initialization races by forcing the end of + * the current grace period to be completely recorded in all of + * the rcu_node structures before the beginning of the next grace + * period is recorded in any of the rcu_node structures. */ + new_gp_seq = rsp->gp_seq; + rcu_seq_end(&new_gp_seq); rcu_for_each_node_breadth_first(rsp, rnp) { raw_spin_lock_irq_rcu_node(rnp); - WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); + if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) + dump_blkd_tasks(rsp, rnp, 10); WARN_ON_ONCE(rnp->qsmask); - WRITE_ONCE(rnp->completed, rsp->gpnum); + WRITE_ONCE(rnp->gp_seq, new_gp_seq); rdp = this_cpu_ptr(rsp->rda); if (rnp == rdp->mynode) needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; @@ -2100,26 +2117,28 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) rcu_gp_slow(rsp, gp_cleanup_delay); } rnp = rcu_get_root(rsp); - raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */ + raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */ /* Declare grace period done. */ - WRITE_ONCE(rsp->completed, rsp->gpnum); - trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); + rcu_seq_end(&rsp->gp_seq); + trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end")); rsp->gp_state = RCU_GP_IDLE; /* Check for GP requests since above loop. */ rdp = this_cpu_ptr(rsp->rda); - if (need_any_future_gp(rnp)) { - trace_rcu_this_gp(rnp, rdp, rsp->completed - 1, + if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) { + trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed, TPS("CleanupMore")); needgp = true; } /* Advance CBs to reduce false positives below. */ if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) { WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), + rsp->gp_req_activity = jiffies; + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); + } else { + WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT); } - WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT); raw_spin_unlock_irq_rcu_node(rnp); } @@ -2141,10 +2160,10 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Handle grace-period start. */ for (;;) { trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; - swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & + swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); rsp->gp_state = RCU_GP_DONE_GPS; /* Locking provides needed memory barrier. */ @@ -2154,17 +2173,13 @@ static int __noreturn rcu_gp_kthread(void *arg) WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("reqwaitsig")); } /* Handle quiescent-state forcing. */ first_gp_fqs = true; j = jiffies_till_first_fqs; - if (j > HZ) { - j = HZ; - jiffies_till_first_fqs = HZ; - } ret = 0; for (;;) { if (!ret) { @@ -2173,10 +2188,10 @@ static int __noreturn rcu_gp_kthread(void *arg) jiffies + 3 * j); } trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; - ret = swait_event_idle_timeout(rsp->gp_wq, + ret = swait_event_idle_timeout_exclusive(rsp->gp_wq, rcu_gp_fqs_check_wake(rsp, &gf), j); rsp->gp_state = RCU_GP_DOING_FQS; /* Locking provides needed memory barriers. */ @@ -2188,31 +2203,24 @@ static int __noreturn rcu_gp_kthread(void *arg) if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) || (gf & RCU_GP_FLAG_FQS)) { trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqsstart")); rcu_gp_fqs(rsp, first_gp_fqs); first_gp_fqs = false; trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqsend")); cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); ret = 0; /* Force full wait till next FQS. */ j = jiffies_till_next_fqs; - if (j > HZ) { - j = HZ; - jiffies_till_next_fqs = HZ; - } else if (j < 1) { - j = 1; - jiffies_till_next_fqs = 1; - } } else { /* Deal with stray signal. */ cond_resched_tasks_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gpnum), + READ_ONCE(rsp->gp_seq), TPS("fqswaitsig")); ret = 1; /* Keep old FQS timing. */ j = jiffies; @@ -2256,8 +2264,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) * must be represented by the same rcu_node structure (which need not be a * leaf rcu_node structure, though it often will be). The gps parameter * is the grace-period snapshot, which means that the quiescent states - * are valid only if rnp->gpnum is equal to gps. That structure's lock + * are valid only if rnp->gp_seq is equal to gps. That structure's lock * must be held upon entry, and it is released before return. + * + * As a special case, if mask is zero, the bit-already-cleared check is + * disabled. This allows propagating quiescent state due to resumed tasks + * during grace-period initialization. */ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, @@ -2271,7 +2283,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, /* Walk up the rcu_node hierarchy. */ for (;;) { - if (!(rnp->qsmask & mask) || rnp->gpnum != gps) { + if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) { /* * Our bit has already been cleared, or the @@ -2284,7 +2296,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, WARN_ON_ONCE(!rcu_is_leaf_node(rnp) && rcu_preempt_blocked_readers_cgp(rnp)); rnp->qsmask &= ~mask; - trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum, + trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq, mask, rnp->qsmask, rnp->level, rnp->grplo, rnp->grphi, !!rnp->gp_tasks); @@ -2294,6 +2306,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } + rnp->completedqs = rnp->gp_seq; mask = rnp->grpmask; if (rnp->parent == NULL) { @@ -2323,8 +2336,9 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * irqs disabled, and this lock is released upon return, but irqs remain * disabled. */ -static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long flags) +static void __maybe_unused +rcu_report_unblock_qs_rnp(struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { unsigned long gps; @@ -2332,12 +2346,15 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, struct rcu_node *rnp_p; raw_lockdep_assert_held_rcu_node(rnp); - if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || - rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { + if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) || + WARN_ON_ONCE(rsp != rcu_state_p) || + WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) || + rnp->qsmask != 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; /* Still need more quiescent states! */ } + rnp->completedqs = rnp->gp_seq; rnp_p = rnp->parent; if (rnp_p == NULL) { /* @@ -2348,8 +2365,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, return; } - /* Report up the rest of the hierarchy, tracking current ->gpnum. */ - gps = rnp->gpnum; + /* Report up the rest of the hierarchy, tracking current ->gp_seq. */ + gps = rnp->gp_seq; mask = rnp->grpmask; raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */ @@ -2370,8 +2387,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) rnp = rdp->mynode; raw_spin_lock_irqsave_rcu_node(rnp, flags); - if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum || - rnp->completed == rnp->gpnum || rdp->gpwrap) { + if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq || + rdp->gpwrap) { /* * The grace period in which this quiescent state was @@ -2396,7 +2413,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) */ needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); /* ^^^ Released rnp->lock */ if (needwake) rcu_gp_kthread_wake(rsp); @@ -2441,17 +2458,16 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) */ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { - RCU_TRACE(unsigned long mask;) + RCU_TRACE(bool blkd;) RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);) RCU_TRACE(struct rcu_node *rnp = rdp->mynode;) if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return; - RCU_TRACE(mask = rdp->grpmask;) - trace_rcu_grace_period(rsp->name, - rnp->gpnum + 1 - !!(rnp->qsmask & mask), - TPS("cpuofl")); + RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);) + trace_rcu_grace_period(rsp->name, rnp->gp_seq, + blkd ? TPS("cpuofl") : TPS("cpuofl-bgp")); } /* @@ -2463,7 +2479,7 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) * This function therefore goes up the tree of rcu_node structures, * clearing the corresponding bits in the ->qsmaskinit fields. Note that * the leaf rcu_node structure's ->qsmaskinit field has already been - * updated + * updated. * * This function does check that the specified rcu_node structure has * all CPUs offline and no blocked tasks, so it is OK to invoke it @@ -2476,9 +2492,10 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; - raw_lockdep_assert_held_rcu_node(rnp); + raw_lockdep_assert_held_rcu_node(rnp_leaf); if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || - rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) + WARN_ON_ONCE(rnp_leaf->qsmaskinit) || + WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf))) return; for (;;) { mask = rnp->grpmask; @@ -2487,7 +2504,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) break; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ rnp->qsmaskinit &= ~mask; - rnp->qsmask &= ~mask; + /* Between grace periods, so better already be zero! */ + WARN_ON_ONCE(rnp->qsmask); if (rnp->qsmaskinit) { raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ @@ -2630,6 +2648,7 @@ void rcu_check_callbacks(int user) rcu_sched_qs(); rcu_bh_qs(); + rcu_note_voluntary_context_switch(current); } else if (!in_softirq()) { @@ -2645,8 +2664,7 @@ void rcu_check_callbacks(int user) rcu_preempt_check_callbacks(); if (rcu_pending()) invoke_rcu_core(); - if (user) - rcu_note_voluntary_context_switch(current); + trace_rcu_utilization(TPS("End scheduler-tick")); } @@ -2681,17 +2699,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) /* rcu_initiate_boost() releases rnp->lock */ continue; } - if (rnp->parent && - (rnp->parent->qsmask & rnp->grpmask)) { - /* - * Race between grace-period - * initialization and task exiting RCU - * read-side critical section: Report. - */ - rcu_report_unblock_qs_rnp(rsp, rnp, flags); - /* rcu_report_unblock_qs_rnp() rlses ->lock */ - continue; - } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + continue; } for_each_leaf_node_possible_cpu(rnp, cpu) { unsigned long bit = leaf_node_cpu_bit(rnp, cpu); @@ -2701,8 +2710,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) } } if (mask != 0) { - /* Idle/offline CPUs, report (releases rnp->lock. */ - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags); + /* Idle/offline CPUs, report (releases rnp->lock). */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); } else { /* Nothing to do here, so just drop the lock. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2747,6 +2756,65 @@ static void force_quiescent_state(struct rcu_state *rsp) } /* + * This function checks for grace-period requests that fail to motivate + * RCU to come out of its idle mode. + */ +static void +rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) +{ + const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ; + unsigned long flags; + unsigned long j; + struct rcu_node *rnp_root = rcu_get_root(rsp); + static atomic_t warned = ATOMIC_INIT(0); + + if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed)) + return; + j = jiffies; /* Expensive access, and in common case don't get here. */ + if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) || + atomic_read(&warned)) + return; + + raw_spin_lock_irqsave_rcu_node(rnp, flags); + j = jiffies; + if (rcu_gp_in_progress(rsp) || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || + time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) || + atomic_read(&warned)) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + /* Hold onto the leaf lock to make others see warned==1. */ + + if (rnp_root != rnp) + raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ + j = jiffies; + if (rcu_gp_in_progress(rsp) || + ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || + time_before(j, rsp->gp_req_activity + gpssdelay) || + time_before(j, rsp->gp_activity + gpssdelay) || + atomic_xchg(&warned, 1)) { + raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */ + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n", + __func__, (long)READ_ONCE(rsp->gp_seq), + (long)READ_ONCE(rnp_root->gp_seq_needed), + j - rsp->gp_req_activity, j - rsp->gp_activity, + rsp->gp_flags, rsp->gp_state, rsp->name, + rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL); + WARN_ON(1); + if (rnp_root != rnp) + raw_spin_unlock_rcu_node(rnp_root); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); +} + +/* * This does the RCU core processing work for the specified rcu_state * and rcu_data structures. This may be called only from the CPU to * whom the rdp belongs. @@ -2755,9 +2823,8 @@ static void __rcu_process_callbacks(struct rcu_state *rsp) { unsigned long flags; - bool needwake; struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); - struct rcu_node *rnp; + struct rcu_node *rnp = rdp->mynode; WARN_ON_ONCE(!rdp->beenonline); @@ -2768,18 +2835,13 @@ __rcu_process_callbacks(struct rcu_state *rsp) if (!rcu_gp_in_progress(rsp) && rcu_segcblist_is_enabled(&rdp->cblist)) { local_irq_save(flags); - if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) { - local_irq_restore(flags); - } else { - rnp = rdp->mynode; - raw_spin_lock_rcu_node(rnp); /* irqs disabled. */ - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (needwake) - rcu_gp_kthread_wake(rsp); - } + if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) + rcu_accelerate_cbs_unlocked(rsp, rnp, rdp); + local_irq_restore(flags); } + rcu_check_gp_start_stall(rsp, rnp, rdp); + /* If there are callbacks ready, invoke them. */ if (rcu_segcblist_ready_cbs(&rdp->cblist)) invoke_rcu_callbacks(rsp, rdp); @@ -2833,8 +2895,6 @@ static void invoke_rcu_core(void) static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, struct rcu_head *head, unsigned long flags) { - bool needwake; - /* * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. @@ -2861,13 +2921,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, /* Start a new grace period if one not already started. */ if (!rcu_gp_in_progress(rsp)) { - struct rcu_node *rnp = rdp->mynode; - - raw_spin_lock_rcu_node(rnp); - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); - raw_spin_unlock_rcu_node(rnp); - if (needwake) - rcu_gp_kthread_wake(rsp); + rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp); } else { /* Give the grace period a kick. */ rdp->blimit = LONG_MAX; @@ -3037,7 +3091,7 @@ EXPORT_SYMBOL_GPL(kfree_call_rcu); * when there was in fact only one the whole time, as this just adds * some overhead: RCU still operates correctly. */ -static inline int rcu_blocking_is_gp(void) +static int rcu_blocking_is_gp(void) { int ret; @@ -3136,16 +3190,10 @@ unsigned long get_state_synchronize_rcu(void) { /* * Any prior manipulation of RCU-protected data must happen - * before the load from ->gpnum. + * before the load from ->gp_seq. */ smp_mb(); /* ^^^ */ - - /* - * Make sure this load happens before the purportedly - * time-consuming work between get_state_synchronize_rcu() - * and cond_synchronize_rcu(). - */ - return smp_load_acquire(&rcu_state_p->gpnum); + return rcu_seq_snap(&rcu_state_p->gp_seq); } EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); @@ -3165,15 +3213,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); */ void cond_synchronize_rcu(unsigned long oldstate) { - unsigned long newstate; - - /* - * Ensure that this load happens before any RCU-destructive - * actions the caller might carry out after we return. - */ - newstate = smp_load_acquire(&rcu_state_p->completed); - if (ULONG_CMP_GE(oldstate, newstate)) + if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate)) synchronize_rcu(); + else + smp_mb(); /* Ensure GP ends before subsequent accesses. */ } EXPORT_SYMBOL_GPL(cond_synchronize_rcu); @@ -3188,16 +3231,10 @@ unsigned long get_state_synchronize_sched(void) { /* * Any prior manipulation of RCU-protected data must happen - * before the load from ->gpnum. + * before the load from ->gp_seq. */ smp_mb(); /* ^^^ */ - - /* - * Make sure this load happens before the purportedly - * time-consuming work between get_state_synchronize_sched() - * and cond_synchronize_sched(). - */ - return smp_load_acquire(&rcu_sched_state.gpnum); + return rcu_seq_snap(&rcu_sched_state.gp_seq); } EXPORT_SYMBOL_GPL(get_state_synchronize_sched); @@ -3217,15 +3254,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_sched); */ void cond_synchronize_sched(unsigned long oldstate) { - unsigned long newstate; - - /* - * Ensure that this load happens before any RCU-destructive - * actions the caller might carry out after we return. - */ - newstate = smp_load_acquire(&rcu_sched_state.completed); - if (ULONG_CMP_GE(oldstate, newstate)) + if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate)) synchronize_sched(); + else + smp_mb(); /* Ensure GP ends before subsequent accesses. */ } EXPORT_SYMBOL_GPL(cond_synchronize_sched); @@ -3261,12 +3293,8 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) return 1; - /* Has another RCU grace period completed? */ - if (READ_ONCE(rnp->completed) != rdp->completed) /* outside lock */ - return 1; - - /* Has a new RCU grace period started? */ - if (READ_ONCE(rnp->gpnum) != rdp->gpnum || + /* Have RCU grace period completed or started? */ + if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq || unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */ return 1; @@ -3298,7 +3326,7 @@ static int rcu_pending(void) * non-NULL, store an indication of whether all callbacks are lazy. * (If there are no callbacks, all of them are deemed to be lazy.) */ -static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy) +static bool rcu_cpu_has_callbacks(bool *all_lazy) { bool al = true; bool hc = false; @@ -3484,17 +3512,22 @@ EXPORT_SYMBOL_GPL(rcu_barrier_sched); static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) { long mask; + long oldmask; struct rcu_node *rnp = rnp_leaf; - raw_lockdep_assert_held_rcu_node(rnp); + raw_lockdep_assert_held_rcu_node(rnp_leaf); + WARN_ON_ONCE(rnp->wait_blkd_tasks); for (;;) { mask = rnp->grpmask; rnp = rnp->parent; if (rnp == NULL) return; raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */ + oldmask = rnp->qsmaskinit; rnp->qsmaskinit |= mask; raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */ + if (oldmask) + return; } } @@ -3511,6 +3544,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1); WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks))); + rdp->rcu_ofl_gp_seq = rsp->gp_seq; + rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED; + rdp->rcu_onl_gp_seq = rsp->gp_seq; + rdp->rcu_onl_gp_flags = RCU_GP_CLEANED; rdp->cpu = cpu; rdp->rsp = rsp; rcu_boot_init_nocb_percpu_data(rdp); @@ -3518,9 +3555,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) /* * Initialize a CPU's per-CPU RCU data. Note that only one online or - * offline event can be happening at a given time. Note also that we - * can accept some slop in the rsp->completed access due to the fact - * that this CPU cannot possibly have any RCU callbacks in flight yet. + * offline event can be happening at a given time. Note also that we can + * accept some slop in the rsp->gp_seq access due to the fact that this + * CPU cannot possibly have any RCU callbacks in flight yet. */ static void rcu_init_percpu_data(int cpu, struct rcu_state *rsp) @@ -3549,14 +3586,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ rdp->beenonline = true; /* We have now been online. */ - rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ - rdp->completed = rnp->completed; + rdp->gp_seq = rnp->gp_seq; + rdp->gp_seq_needed = rnp->gp_seq; rdp->cpu_no_qs.b.norm = true; rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu); rdp->core_needs_qs = false; rdp->rcu_iw_pending = false; - rdp->rcu_iw_gpnum = rnp->gpnum - 1; - trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); + rdp->rcu_iw_gp_seq = rnp->gp_seq - 1; + trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } @@ -3705,7 +3742,15 @@ void rcu_cpu_starting(unsigned int cpu) nbits = bitmap_weight(&oldmask, BITS_PER_LONG); /* Allow lockless access for expedited grace periods. */ smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */ - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ + rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq); + rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags); + if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */ + /* Report QS -after- changing ->qsmaskinitnext! */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + } else { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } } smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } @@ -3713,7 +3758,7 @@ void rcu_cpu_starting(unsigned int cpu) #ifdef CONFIG_HOTPLUG_CPU /* * The CPU is exiting the idle loop into the arch_cpu_idle_dead() - * function. We now remove it from the rcu_node tree's ->qsmaskinit + * function. We now remove it from the rcu_node tree's ->qsmaskinitnext * bit masks. */ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) @@ -3725,9 +3770,18 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; + spin_lock(&rsp->ofl_lock); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ + rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq); + rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags); + if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */ + /* Report quiescent state -before- changing ->qsmaskinitnext! */ + rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); + } rnp->qsmaskinitnext &= ~mask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + spin_unlock(&rsp->ofl_lock); } /* @@ -3839,12 +3893,16 @@ static int __init rcu_spawn_gp_kthread(void) struct task_struct *t; /* Force priority into range. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) + if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2 + && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) + kthread_prio = 2; + else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) kthread_prio = 1; else if (kthread_prio < 0) kthread_prio = 0; else if (kthread_prio > 99) kthread_prio = 99; + if (kthread_prio != kthread_prio_in) pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n", kthread_prio, kthread_prio_in); @@ -3928,8 +3986,9 @@ static void __init rcu_init_one(struct rcu_state *rsp) raw_spin_lock_init(&rnp->fqslock); lockdep_set_class_and_name(&rnp->fqslock, &rcu_fqs_class[i], fqs[i]); - rnp->gpnum = rsp->gpnum; - rnp->completed = rsp->completed; + rnp->gp_seq = rsp->gp_seq; + rnp->gp_seq_needed = rsp->gp_seq; + rnp->completedqs = rsp->gp_seq; rnp->qsmask = 0; rnp->qsmaskinit = 0; rnp->grplo = j * cpustride; @@ -3997,7 +4056,7 @@ static void __init rcu_init_geometry(void) if (rcu_fanout_leaf == RCU_FANOUT_LEAF && nr_cpu_ids == NR_CPUS) return; - pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n", + pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n", rcu_fanout_leaf, nr_cpu_ids); /* diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 78e051dffc5b..4e74df768c57 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -81,18 +81,16 @@ struct rcu_node { raw_spinlock_t __private lock; /* Root rcu_node's lock protects */ /* some rcu_state fields as well as */ /* following. */ - unsigned long gpnum; /* Current grace period for this node. */ - /* This will either be equal to or one */ - /* behind the root rcu_node's gpnum. */ - unsigned long completed; /* Last GP completed for this node. */ - /* This will either be equal to or one */ - /* behind the root rcu_node's gpnum. */ + unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */ + unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */ + unsigned long completedqs; /* All QSes done for this node. */ unsigned long qsmask; /* CPUs or groups that need to switch in */ /* order for current grace period to proceed.*/ /* In leaf rcu_node, each bit corresponds to */ /* an rcu_data structure, otherwise, each */ /* bit corresponds to a child rcu_node */ /* structure. */ + unsigned long rcu_gp_init_mask; /* Mask of offline CPUs at GP init. */ unsigned long qsmaskinit; /* Per-GP initial value for qsmask. */ /* Initialized from ->qsmaskinitnext at the */ @@ -158,7 +156,6 @@ struct rcu_node { struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ - u8 need_future_gp[4]; /* Counts of upcoming GP requests. */ raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; spinlock_t exp_lock ____cacheline_internodealigned_in_smp; @@ -168,22 +165,6 @@ struct rcu_node { bool exp_need_flush; /* Need to flush workitem? */ } ____cacheline_internodealigned_in_smp; -/* Accessors for ->need_future_gp[] array. */ -#define need_future_gp_mask() \ - (ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1) -#define need_future_gp_element(rnp, c) \ - ((rnp)->need_future_gp[(c) & need_future_gp_mask()]) -#define need_any_future_gp(rnp) \ -({ \ - int __i; \ - bool __nonzero = false; \ - \ - for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++) \ - __nonzero = __nonzero || \ - READ_ONCE((rnp)->need_future_gp[__i]); \ - __nonzero; \ -}) - /* * Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and * are indexed relative to this interval rather than the global CPU ID space. @@ -206,16 +187,14 @@ union rcu_noqs { /* Per-CPU data for read-copy update. */ struct rcu_data { /* 1) quiescent-state and grace-period handling : */ - unsigned long completed; /* Track rsp->completed gp number */ - /* in order to detect GP end. */ - unsigned long gpnum; /* Highest gp number that this CPU */ - /* is aware of having started. */ + unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */ + unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */ unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ /* for rcu_all_qs() invocations. */ union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ - bool gpwrap; /* Possible gpnum/completed wrap. */ + bool gpwrap; /* Possible ->gp_seq wrap. */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ unsigned long ticks_this_gp; /* The number of scheduling-clock */ @@ -239,7 +218,6 @@ struct rcu_data { /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ - unsigned long offline_fqs; /* Kicked due to being offline. */ unsigned long cond_resched_completed; /* Grace period that needs help */ /* from cond_resched(). */ @@ -278,12 +256,16 @@ struct rcu_data { /* Leader CPU takes GP-end wakeups. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ - /* 7) RCU CPU stall data. */ + /* 7) Diagnostic data, including RCU CPU stall warnings. */ unsigned int softirq_snap; /* Snapshot of softirq activity. */ /* ->rcu_iw* fields protected by leaf rcu_node ->lock. */ struct irq_work rcu_iw; /* Check for non-irq activity. */ bool rcu_iw_pending; /* Is ->rcu_iw pending? */ - unsigned long rcu_iw_gpnum; /* ->gpnum associated with ->rcu_iw. */ + unsigned long rcu_iw_gp_seq; /* ->gp_seq associated with ->rcu_iw. */ + unsigned long rcu_ofl_gp_seq; /* ->gp_seq at last offline. */ + short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */ + unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */ + short rcu_onl_gp_flags; /* ->gp_flags at last online. */ int cpu; struct rcu_state *rsp; @@ -340,8 +322,7 @@ struct rcu_state { u8 boost ____cacheline_internodealigned_in_smp; /* Subject to priority boost. */ - unsigned long gpnum; /* Current gp number. */ - unsigned long completed; /* # of last completed gp. */ + unsigned long gp_seq; /* Grace-period sequence #. */ struct task_struct *gp_kthread; /* Task for grace periods. */ struct swait_queue_head gp_wq; /* Where GP task waits. */ short gp_flags; /* Commands for GP task. */ @@ -373,6 +354,8 @@ struct rcu_state { /* but in jiffies. */ unsigned long gp_activity; /* Time of last GP kthread */ /* activity in jiffies. */ + unsigned long gp_req_activity; /* Time of last GP request */ + /* in jiffies. */ unsigned long jiffies_stall; /* Time at which to check */ /* for CPU stalls. */ unsigned long jiffies_resched; /* Time at which to resched */ @@ -384,6 +367,10 @@ struct rcu_state { const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ struct list_head flavors; /* List of RCU flavors. */ + + spinlock_t ofl_lock ____cacheline_internodealigned_in_smp; + /* Synchronize offline with */ + /* GP pre-initialization. */ }; /* Values for rcu_state structure's gp_flags field. */ @@ -394,16 +381,20 @@ struct rcu_state { #define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */ #define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ #define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */ -#define RCU_GP_WAIT_FQS 3 /* Wait for force-quiescent-state time. */ -#define RCU_GP_DOING_FQS 4 /* Wait done for force-quiescent-state time. */ -#define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */ -#define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */ +#define RCU_GP_ONOFF 3 /* Grace-period initialization hotplug. */ +#define RCU_GP_INIT 4 /* Grace-period initialization. */ +#define RCU_GP_WAIT_FQS 5 /* Wait for force-quiescent-state time. */ +#define RCU_GP_DOING_FQS 6 /* Wait done for force-quiescent-state time. */ +#define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */ +#define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */ #ifndef RCU_TREE_NONCORE static const char * const gp_state_names[] = { "RCU_GP_IDLE", "RCU_GP_WAIT_GPS", "RCU_GP_DONE_GPS", + "RCU_GP_ONOFF", + "RCU_GP_INIT", "RCU_GP_WAIT_FQS", "RCU_GP_DOING_FQS", "RCU_GP_CLEANUP", @@ -449,10 +440,13 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); static int rcu_print_task_exp_stall(struct rcu_node *rnp); -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); +static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, + struct rcu_node *rnp); static void rcu_preempt_check_callbacks(void); void call_rcu(struct rcu_head *head, rcu_callback_t func); static void __init __rcu_init_preempt(void); +static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, + int ncheck); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static void invoke_rcu_callbacks_kthread(void); @@ -489,7 +483,6 @@ static void __init rcu_spawn_nocb_kthreads(void); #ifdef CONFIG_RCU_NOCB_CPU static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp); #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ -static void __maybe_unused rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); static void rcu_bind_gp_kthread(void); static bool rcu_nohz_full_cpu(struct rcu_state *rsp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index d40708e8c5d6..0b2c2ad69629 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - swake_up(&rsp->expedited_wq); + swake_up_one(&rsp->expedited_wq); } break; } @@ -472,6 +472,7 @@ retry_ipi: static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, smp_call_func_t func) { + int cpu; struct rcu_node *rnp; trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset")); @@ -486,13 +487,20 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, rnp->rew.rew_func = func; rnp->rew.rew_rsp = rsp; if (!READ_ONCE(rcu_par_gp_wq) || - rcu_scheduler_active != RCU_SCHEDULER_RUNNING) { - /* No workqueues yet. */ + rcu_scheduler_active != RCU_SCHEDULER_RUNNING || + rcu_is_last_leaf_node(rsp, rnp)) { + /* No workqueues yet or last leaf, do direct call. */ sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work); continue; } INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); - queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work); + preempt_disable(); + cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask); + /* If all offline, queue the work on an unbound CPU. */ + if (unlikely(cpu > rnp->grphi)) + cpu = WORK_CPU_UNBOUND; + queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); + preempt_enable(); rnp->exp_need_flush = true; } @@ -518,7 +526,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) jiffies_start = jiffies; for (;;) { - ret = swait_event_timeout( + ret = swait_event_timeout_exclusive( rsp->expedited_wq, sync_rcu_preempt_exp_done_unlocked(rnp_root), jiffies_stall); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7fd12039e512..a97c20ea9bce 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -74,8 +74,8 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tRCU event tracing is enabled.\n"); if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) || (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32)) - pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", - RCU_FANOUT); + pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d.\n", + RCU_FANOUT); if (rcu_fanout_exact) pr_info("\tHierarchical RCU autobalancing is disabled.\n"); if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ)) @@ -88,11 +88,13 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", RCU_FANOUT_LEAF); if (rcu_fanout_leaf != RCU_FANOUT_LEAF) - pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); + pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", + rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%u.\n", NR_CPUS, nr_cpu_ids); #ifdef CONFIG_RCU_BOOST - pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY); + pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", + kthread_prio, CONFIG_RCU_BOOST_DELAY); #endif if (blimit != DEFAULT_RCU_BLIMIT) pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit); @@ -127,6 +129,7 @@ static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data; static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); +static void rcu_read_unlock_special(struct task_struct *t); /* * Tell them what RCU they are running. @@ -183,6 +186,9 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) raw_lockdep_assert_held_rcu_node(rnp); WARN_ON_ONCE(rdp->mynode != rnp); WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); + /* RCU better not be waiting on newly onlined CPUs! */ + WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask & + rdp->grpmask); /* * Decide where to queue the newly blocked task. In theory, @@ -260,8 +266,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * ->exp_tasks pointers, respectively, to reference the newly * blocked tasks. */ - if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) + if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) { rnp->gp_tasks = &t->rcu_node_entry; + WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq); + } if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) rnp->exp_tasks = &t->rcu_node_entry; WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) != @@ -286,20 +294,24 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) } /* - * Record a preemptible-RCU quiescent state for the specified CPU. Note - * that this just means that the task currently running on the CPU is - * not in a quiescent state. There might be any number of tasks blocked - * while in an RCU read-side critical section. + * Record a preemptible-RCU quiescent state for the specified CPU. + * Note that this does not necessarily mean that the task currently running + * on the CPU is in a quiescent state: Instead, it means that the current + * grace period need not wait on any RCU read-side critical section that + * starts later on this CPU. It also means that if the current task is + * in an RCU read-side critical section, it has already added itself to + * some leaf rcu_node structure's ->blkd_tasks list. In addition to the + * current task, there might be any number of other tasks blocked while + * in an RCU read-side critical section. * - * As with the other rcu_*_qs() functions, callers to this function - * must disable preemption. + * Callers to this function must disable preemption. */ static void rcu_preempt_qs(void) { RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n"); if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), - __this_cpu_read(rcu_data_p->gpnum), + __this_cpu_read(rcu_data_p->gp_seq), TPS("cpuqs")); __this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ @@ -348,8 +360,8 @@ static void rcu_preempt_note_context_switch(bool preempt) trace_rcu_preempt_task(rdp->rsp->name, t->pid, (rnp->qsmask & rdp->grpmask) - ? rnp->gpnum - : rnp->gpnum + 1); + ? rnp->gp_seq + : rcu_seq_snap(&rnp->gp_seq)); rcu_preempt_ctxt_queue(rnp, rdp); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { @@ -456,7 +468,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -void rcu_read_unlock_special(struct task_struct *t) +static void rcu_read_unlock_special(struct task_struct *t) { bool empty_exp; bool empty_norm; @@ -535,13 +547,15 @@ void rcu_read_unlock_special(struct task_struct *t) WARN_ON_ONCE(rnp != t->rcu_blocked_node); WARN_ON_ONCE(!rcu_is_leaf_node(rnp)); empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); + WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq && + (!empty_norm || rnp->qsmask)); empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); t->rcu_blocked_node = NULL; trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), - rnp->gpnum, t->pid); + rnp->gp_seq, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) rnp->gp_tasks = np; if (&t->rcu_node_entry == rnp->exp_tasks) @@ -562,7 +576,7 @@ void rcu_read_unlock_special(struct task_struct *t) empty_exp_now = sync_rcu_preempt_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), - rnp->gpnum, + rnp->gp_seq, 0, rnp->qsmask, rnp->level, rnp->grplo, @@ -686,24 +700,27 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be - * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock + * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock * must be held by the caller. * * Also, if there are blocked tasks on the list, they automatically * block the newly created grace period, so set up ->gp_tasks accordingly. */ -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +static void +rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp) { struct task_struct *t; RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n"); - WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); - if (rcu_preempt_has_tasks(rnp)) { + if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) + dump_blkd_tasks(rsp, rnp, 10); + if (rcu_preempt_has_tasks(rnp) && + (rnp->qsmaskinit || rnp->wait_blkd_tasks)) { rnp->gp_tasks = rnp->blkd_tasks.next; t = container_of(rnp->gp_tasks, struct task_struct, rcu_node_entry); trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"), - rnp->gpnum, t->pid); + rnp->gp_seq, t->pid); } WARN_ON_ONCE(rnp->qsmask); } @@ -717,6 +734,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) */ static void rcu_preempt_check_callbacks(void) { + struct rcu_state *rsp = &rcu_preempt_state; struct task_struct *t = current; if (t->rcu_read_lock_nesting == 0) { @@ -725,7 +743,9 @@ static void rcu_preempt_check_callbacks(void) } if (t->rcu_read_lock_nesting > 0 && __this_cpu_read(rcu_data_p->core_needs_qs) && - __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm)) + __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm) && + !t->rcu_read_unlock_special.b.need_qs && + time_after(jiffies, rsp->gp_start + HZ)) t->rcu_read_unlock_special.b.need_qs = true; } @@ -841,6 +861,47 @@ void exit_rcu(void) __rcu_read_unlock(); } +/* + * Dump the blocked-tasks state, but limit the list dump to the + * specified number of elements. + */ +static void +dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) +{ + int cpu; + int i; + struct list_head *lhp; + bool onl; + struct rcu_data *rdp; + struct rcu_node *rnp1; + + raw_lockdep_assert_held_rcu_node(rnp); + pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n", + __func__, rnp->grplo, rnp->grphi, rnp->level, + (long)rnp->gp_seq, (long)rnp->completedqs); + for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent) + pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n", + __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext); + pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n", + __func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks); + pr_info("%s: ->blkd_tasks", __func__); + i = 0; + list_for_each(lhp, &rnp->blkd_tasks) { + pr_cont(" %p", lhp); + if (++i >= 10) + break; + } + pr_cont("\n"); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { + rdp = per_cpu_ptr(rsp->rda, cpu); + onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); + pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n", + cpu, ".o"[onl], + (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, + (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); + } +} + #else /* #ifdef CONFIG_PREEMPT_RCU */ static struct rcu_state *const rcu_state_p = &rcu_sched_state; @@ -911,7 +972,8 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. */ -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) +static void +rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp) { WARN_ON_ONCE(rnp->qsmask); } @@ -949,6 +1011,15 @@ void exit_rcu(void) { } +/* + * Dump the guaranteed-empty blocked-tasks state. Trust but verify. + */ +static void +dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) +{ + WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks)); +} + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_BOOST @@ -1433,7 +1504,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) * completed since we last checked and there are * callbacks not yet ready to invoke. */ - if ((rdp->completed != rnp->completed || + if ((rcu_seq_completed_gp(rdp->gp_seq, + rcu_seq_current(&rnp->gp_seq)) || unlikely(READ_ONCE(rdp->gpwrap))) && rcu_segcblist_pend_cbs(&rdp->cblist)) note_gp_changes(rsp, rdp); @@ -1720,16 +1792,16 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) */ touch_nmi_watchdog(); - if (rsp->gpnum == rdp->gpnum) { + ticks_value = rcu_seq_ctr(rsp->gp_seq - rdp->gp_seq); + if (ticks_value) { + ticks_title = "GPs behind"; + } else { ticks_title = "ticks this GP"; ticks_value = rdp->ticks_this_gp; - } else { - ticks_title = "GPs behind"; - ticks_value = rsp->gpnum - rdp->gpnum; } print_cpu_stall_fast_no_hz(fast_no_hz, cpu); - delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum; - pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%ld softirq=%u/%u fqs=%ld %s\n", + delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq); + pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n", cpu, "O."[!!cpu_online(cpu)], "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], @@ -1817,7 +1889,7 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) { - return &rnp->nocb_gp_wq[rnp->completed & 0x1]; + return &rnp->nocb_gp_wq[rcu_seq_ctr(rnp->gp_seq) & 0x1]; } static void rcu_init_one_nocb(struct rcu_node *rnp) @@ -1854,8 +1926,8 @@ static void __wake_nocb_leader(struct rcu_data *rdp, bool force, WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); del_timer(&rdp->nocb_timer); raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); - smp_mb(); /* ->nocb_leader_sleep before swake_up(). */ - swake_up(&rdp_leader->nocb_wq); + smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */ + swake_up_one(&rdp_leader->nocb_wq); } else { raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); } @@ -2069,12 +2141,17 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) bool needwake; struct rcu_node *rnp = rdp->mynode; - raw_spin_lock_irqsave_rcu_node(rnp, flags); - c = rcu_cbs_completed(rdp->rsp, rnp); - needwake = rcu_start_this_gp(rnp, rdp, c); - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (needwake) - rcu_gp_kthread_wake(rdp->rsp); + local_irq_save(flags); + c = rcu_seq_snap(&rdp->rsp->gp_seq); + if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { + local_irq_restore(flags); + } else { + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + needwake = rcu_start_this_gp(rnp, rdp, c); + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + if (needwake) + rcu_gp_kthread_wake(rdp->rsp); + } /* * Wait for the grace period. Do so interruptibly to avoid messing @@ -2082,9 +2159,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) */ trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait")); for (;;) { - swait_event_interruptible( - rnp->nocb_gp_wq[c & 0x1], - (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); + swait_event_interruptible_exclusive( + rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1], + (d = rcu_seq_done(&rnp->gp_seq, c))); if (likely(d)) break; WARN_ON(signal_pending(current)); @@ -2111,7 +2188,7 @@ wait_again: /* Wait for callbacks to appear. */ if (!rcu_nocb_poll) { trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep")); - swait_event_interruptible(my_rdp->nocb_wq, + swait_event_interruptible_exclusive(my_rdp->nocb_wq, !READ_ONCE(my_rdp->nocb_leader_sleep)); raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags); my_rdp->nocb_leader_sleep = true; @@ -2176,7 +2253,7 @@ wait_again: raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { /* List was empty, so wake up the follower. */ - swake_up(&rdp->nocb_wq); + swake_up_one(&rdp->nocb_wq); } } @@ -2193,7 +2270,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) { for (;;) { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep")); - swait_event_interruptible(rdp->nocb_wq, + swait_event_interruptible_exclusive(rdp->nocb_wq, READ_ONCE(rdp->nocb_follower_head)); if (smp_load_acquire(&rdp->nocb_follower_head)) { /* ^^^ Ensure CB invocation follows _head test. */ @@ -2569,23 +2646,6 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* - * An adaptive-ticks CPU can potentially execute in kernel mode for an - * arbitrarily long period of time with the scheduling-clock tick turned - * off. RCU will be paying attention to this CPU because it is in the - * kernel, but the CPU cannot be guaranteed to be executing the RCU state - * machine because the scheduling-clock tick has been disabled. Therefore, - * if an adaptive-ticks CPU is failing to respond to the current grace - * period and has not be idle from an RCU perspective, kick it. - */ -static void __maybe_unused rcu_kick_nohz_cpu(int cpu) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_cpu(cpu)) - smp_send_reschedule(cpu); -#endif /* #ifdef CONFIG_NO_HZ_FULL */ -} - -/* * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the * grace-period kthread will do force_quiescent_state() processing? * The idea is to avoid waking up RCU core processing on such a @@ -2610,8 +2670,6 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp) */ static void rcu_bind_gp_kthread(void) { - int __maybe_unused cpu; - if (!tick_nohz_full_enabled()) return; housekeeping_affine(current, HK_FLAG_RCU); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 4c230a60ece4..39cb23d22109 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -507,14 +507,15 @@ early_initcall(check_cpu_stall_init); #ifdef CONFIG_TASKS_RCU /* - * Simple variant of RCU whose quiescent states are voluntary context switch, - * user-space execution, and idle. As such, grace periods can take one good - * long time. There are no read-side primitives similar to rcu_read_lock() - * and rcu_read_unlock() because this implementation is intended to get - * the system into a safe state for some of the manipulations involved in - * tracing and the like. Finally, this implementation does not support - * high call_rcu_tasks() rates from multiple CPUs. If this is required, - * per-CPU callback lists will be needed. + * Simple variant of RCU whose quiescent states are voluntary context + * switch, cond_resched_rcu_qs(), user-space execution, and idle. + * As such, grace periods can take one good long time. There are no + * read-side primitives similar to rcu_read_lock() and rcu_read_unlock() + * because this implementation is intended to get the system into a safe + * state for some of the manipulations involved in tracing and the like. + * Finally, this implementation does not support high call_rcu_tasks() + * rates from multiple CPUs. If this is required, per-CPU callback lists + * will be needed. */ /* Global list of callbacks and associated lock. */ @@ -542,11 +543,11 @@ static struct task_struct *rcu_tasks_kthread_ptr; * period elapses, in other words after all currently executing RCU * read-side critical sections have completed. call_rcu_tasks() assumes * that the read-side critical sections end at a voluntary context - * switch (not a preemption!), entry into idle, or transition to usermode - * execution. As such, there are no read-side primitives analogous to - * rcu_read_lock() and rcu_read_unlock() because this primitive is intended - * to determine that all tasks have passed through a safe state, not so - * much for data-strcuture synchronization. + * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle, + * or transition to usermode execution. As such, there are no read-side + * primitives analogous to rcu_read_lock() and rcu_read_unlock() because + * this primitive is intended to determine that all tasks have passed + * through a safe state, not so much for data-strcuture synchronization. * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. @@ -667,6 +668,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) struct rcu_head *list; struct rcu_head *next; LIST_HEAD(rcu_tasks_holdouts); + int fract; /* Run on housekeeping CPUs by default. Sysadm can move if desired. */ housekeeping_affine(current, HK_FLAG_RCU); @@ -748,13 +750,25 @@ static int __noreturn rcu_tasks_kthread(void *arg) * holdouts. When the list is empty, we are done. */ lastreport = jiffies; - while (!list_empty(&rcu_tasks_holdouts)) { + + /* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/ + fract = 10; + + for (;;) { bool firstreport; bool needreport; int rtst; struct task_struct *t1; - schedule_timeout_interruptible(HZ); + if (list_empty(&rcu_tasks_holdouts)) + break; + + /* Slowly back off waiting for holdouts */ + schedule_timeout_interruptible(HZ/fract); + + if (fract > 1) + fract--; + rtst = READ_ONCE(rcu_task_stall_timeout); needreport = rtst > 0 && time_after(jiffies, lastreport + rtst); @@ -800,6 +814,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) list = next; cond_resched(); } + /* Paranoid sleep to keep this from entering a tight loop */ schedule_timeout_uninterruptible(HZ/10); } } diff --git a/kernel/reboot.c b/kernel/reboot.c index e4ced883d8de..8fb44dec9ad7 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -294,7 +294,7 @@ void kernel_power_off(void) } EXPORT_SYMBOL_GPL(kernel_power_off); -static DEFINE_MUTEX(reboot_mutex); +DEFINE_MUTEX(system_transition_mutex); /* * Reboot system call: for obvious reasons only root may call it, @@ -338,7 +338,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) cmd = LINUX_REBOOT_CMD_HALT; - mutex_lock(&reboot_mutex); + mutex_lock(&system_transition_mutex); switch (cmd) { case LINUX_REBOOT_CMD_RESTART: kernel_restart(NULL); @@ -389,7 +389,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, ret = -EINVAL; break; } - mutex_unlock(&reboot_mutex); + mutex_unlock(&system_transition_mutex); return ret; } diff --git a/kernel/relay.c b/kernel/relay.c index c955b10c973c..04f248644e06 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -39,7 +39,7 @@ static void relay_file_mmap_close(struct vm_area_struct *vma) /* * fault() vm_op implementation for relay file mapping. */ -static int relay_buf_fault(struct vm_fault *vmf) +static vm_fault_t relay_buf_fault(struct vm_fault *vmf) { struct page *page; struct rchan_buf *buf = vmf->vma->vm_private_data; @@ -169,7 +169,8 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan) buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); if (!buf) return NULL; - buf->padding = kmalloc(chan->n_subbufs * sizeof(size_t *), GFP_KERNEL); + buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t *), + GFP_KERNEL); if (!buf->padding) goto free_buf; diff --git a/kernel/resource.c b/kernel/resource.c index b589dda910b3..30e1bc68503b 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -415,6 +415,7 @@ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, return __walk_iomem_res_desc(&res, desc, false, arg, func); } +EXPORT_SYMBOL_GPL(walk_iomem_res_desc); /* * This function calls the @func callback against all memory ranges of type diff --git a/kernel/rseq.c b/kernel/rseq.c new file mode 100644 index 000000000000..c6242d8594dc --- /dev/null +++ b/kernel/rseq.c @@ -0,0 +1,367 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Restartable sequences system call + * + * Copyright (C) 2015, Google, Inc., + * Paul Turner <pjt@google.com> and Andrew Hunter <ahh@google.com> + * Copyright (C) 2015-2018, EfficiOS Inc., + * Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#include <linux/sched.h> +#include <linux/uaccess.h> +#include <linux/syscalls.h> +#include <linux/rseq.h> +#include <linux/types.h> +#include <asm/ptrace.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/rseq.h> + +#define RSEQ_CS_PREEMPT_MIGRATE_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE | \ + RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT) + +/* + * + * Restartable sequences are a lightweight interface that allows + * user-level code to be executed atomically relative to scheduler + * preemption and signal delivery. Typically used for implementing + * per-cpu operations. + * + * It allows user-space to perform update operations on per-cpu data + * without requiring heavy-weight atomic operations. + * + * Detailed algorithm of rseq user-space assembly sequences: + * + * init(rseq_cs) + * cpu = TLS->rseq::cpu_id_start + * [1] TLS->rseq::rseq_cs = rseq_cs + * [start_ip] ---------------------------- + * [2] if (cpu != TLS->rseq::cpu_id) + * goto abort_ip; + * [3] <last_instruction_in_cs> + * [post_commit_ip] ---------------------------- + * + * The address of jump target abort_ip must be outside the critical + * region, i.e.: + * + * [abort_ip] < [start_ip] || [abort_ip] >= [post_commit_ip] + * + * Steps [2]-[3] (inclusive) need to be a sequence of instructions in + * userspace that can handle being interrupted between any of those + * instructions, and then resumed to the abort_ip. + * + * 1. Userspace stores the address of the struct rseq_cs assembly + * block descriptor into the rseq_cs field of the registered + * struct rseq TLS area. This update is performed through a single + * store within the inline assembly instruction sequence. + * [start_ip] + * + * 2. Userspace tests to check whether the current cpu_id field match + * the cpu number loaded before start_ip, branching to abort_ip + * in case of a mismatch. + * + * If the sequence is preempted or interrupted by a signal + * at or after start_ip and before post_commit_ip, then the kernel + * clears TLS->__rseq_abi::rseq_cs, and sets the user-space return + * ip to abort_ip before returning to user-space, so the preempted + * execution resumes at abort_ip. + * + * 3. Userspace critical section final instruction before + * post_commit_ip is the commit. The critical section is + * self-terminating. + * [post_commit_ip] + * + * 4. <success> + * + * On failure at [2], or if interrupted by preempt or signal delivery + * between [1] and [3]: + * + * [abort_ip] + * F1. <failure> + */ + +static int rseq_update_cpu_id(struct task_struct *t) +{ + u32 cpu_id = raw_smp_processor_id(); + + if (put_user(cpu_id, &t->rseq->cpu_id_start)) + return -EFAULT; + if (put_user(cpu_id, &t->rseq->cpu_id)) + return -EFAULT; + trace_rseq_update(t); + return 0; +} + +static int rseq_reset_rseq_cpu_id(struct task_struct *t) +{ + u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED; + + /* + * Reset cpu_id_start to its initial state (0). + */ + if (put_user(cpu_id_start, &t->rseq->cpu_id_start)) + return -EFAULT; + /* + * Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming + * in after unregistration can figure out that rseq needs to be + * registered again. + */ + if (put_user(cpu_id, &t->rseq->cpu_id)) + return -EFAULT; + return 0; +} + +static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs) +{ + struct rseq_cs __user *urseq_cs; + u64 ptr; + u32 __user *usig; + u32 sig; + int ret; + + if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr))) + return -EFAULT; + if (!ptr) { + memset(rseq_cs, 0, sizeof(*rseq_cs)); + return 0; + } + if (ptr >= TASK_SIZE) + return -EINVAL; + urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr; + if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs))) + return -EFAULT; + + if (rseq_cs->start_ip >= TASK_SIZE || + rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE || + rseq_cs->abort_ip >= TASK_SIZE || + rseq_cs->version > 0) + return -EINVAL; + /* Check for overflow. */ + if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip) + return -EINVAL; + /* Ensure that abort_ip is not in the critical section. */ + if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset) + return -EINVAL; + + usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32)); + ret = get_user(sig, usig); + if (ret) + return ret; + + if (current->rseq_sig != sig) { + printk_ratelimited(KERN_WARNING + "Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n", + sig, current->rseq_sig, current->pid, usig); + return -EINVAL; + } + return 0; +} + +static int rseq_need_restart(struct task_struct *t, u32 cs_flags) +{ + u32 flags, event_mask; + int ret; + + /* Get thread flags. */ + ret = get_user(flags, &t->rseq->flags); + if (ret) + return ret; + + /* Take critical section flags into account. */ + flags |= cs_flags; + + /* + * Restart on signal can only be inhibited when restart on + * preempt and restart on migrate are inhibited too. Otherwise, + * a preempted signal handler could fail to restart the prior + * execution context on sigreturn. + */ + if (unlikely((flags & RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL) && + (flags & RSEQ_CS_PREEMPT_MIGRATE_FLAGS) != + RSEQ_CS_PREEMPT_MIGRATE_FLAGS)) + return -EINVAL; + + /* + * Load and clear event mask atomically with respect to + * scheduler preemption. + */ + preempt_disable(); + event_mask = t->rseq_event_mask; + t->rseq_event_mask = 0; + preempt_enable(); + + return !!(event_mask & ~flags); +} + +static int clear_rseq_cs(struct task_struct *t) +{ + /* + * The rseq_cs field is set to NULL on preemption or signal + * delivery on top of rseq assembly block, as well as on top + * of code outside of the rseq assembly block. This performs + * a lazy clear of the rseq_cs field. + * + * Set rseq_cs to NULL. + */ + if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64))) + return -EFAULT; + return 0; +} + +/* + * Unsigned comparison will be true when ip >= start_ip, and when + * ip < start_ip + post_commit_offset. + */ +static bool in_rseq_cs(unsigned long ip, struct rseq_cs *rseq_cs) +{ + return ip - rseq_cs->start_ip < rseq_cs->post_commit_offset; +} + +static int rseq_ip_fixup(struct pt_regs *regs) +{ + unsigned long ip = instruction_pointer(regs); + struct task_struct *t = current; + struct rseq_cs rseq_cs; + int ret; + + ret = rseq_get_rseq_cs(t, &rseq_cs); + if (ret) + return ret; + + /* + * Handle potentially not being within a critical section. + * If not nested over a rseq critical section, restart is useless. + * Clear the rseq_cs pointer and return. + */ + if (!in_rseq_cs(ip, &rseq_cs)) + return clear_rseq_cs(t); + ret = rseq_need_restart(t, rseq_cs.flags); + if (ret <= 0) + return ret; + ret = clear_rseq_cs(t); + if (ret) + return ret; + trace_rseq_ip_fixup(ip, rseq_cs.start_ip, rseq_cs.post_commit_offset, + rseq_cs.abort_ip); + instruction_pointer_set(regs, (unsigned long)rseq_cs.abort_ip); + return 0; +} + +/* + * This resume handler must always be executed between any of: + * - preemption, + * - signal delivery, + * and return to user-space. + * + * This is how we can ensure that the entire rseq critical section, + * consisting of both the C part and the assembly instruction sequence, + * will issue the commit instruction only if executed atomically with + * respect to other threads scheduled on the same CPU, and with respect + * to signal handlers. + */ +void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) +{ + struct task_struct *t = current; + int ret, sig; + + if (unlikely(t->flags & PF_EXITING)) + return; + if (unlikely(!access_ok(VERIFY_WRITE, t->rseq, sizeof(*t->rseq)))) + goto error; + ret = rseq_ip_fixup(regs); + if (unlikely(ret < 0)) + goto error; + if (unlikely(rseq_update_cpu_id(t))) + goto error; + return; + +error: + sig = ksig ? ksig->sig : 0; + force_sigsegv(sig, t); +} + +#ifdef CONFIG_DEBUG_RSEQ + +/* + * Terminate the process if a syscall is issued within a restartable + * sequence. + */ +void rseq_syscall(struct pt_regs *regs) +{ + unsigned long ip = instruction_pointer(regs); + struct task_struct *t = current; + struct rseq_cs rseq_cs; + + if (!t->rseq) + return; + if (!access_ok(VERIFY_READ, t->rseq, sizeof(*t->rseq)) || + rseq_get_rseq_cs(t, &rseq_cs) || in_rseq_cs(ip, &rseq_cs)) + force_sig(SIGSEGV, t); +} + +#endif + +/* + * sys_rseq - setup restartable sequences for caller thread. + */ +SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, + int, flags, u32, sig) +{ + int ret; + + if (flags & RSEQ_FLAG_UNREGISTER) { + /* Unregister rseq for current thread. */ + if (current->rseq != rseq || !current->rseq) + return -EINVAL; + if (current->rseq_len != rseq_len) + return -EINVAL; + if (current->rseq_sig != sig) + return -EPERM; + ret = rseq_reset_rseq_cpu_id(current); + if (ret) + return ret; + current->rseq = NULL; + current->rseq_len = 0; + current->rseq_sig = 0; + return 0; + } + + if (unlikely(flags)) + return -EINVAL; + + if (current->rseq) { + /* + * If rseq is already registered, check whether + * the provided address differs from the prior + * one. + */ + if (current->rseq != rseq || current->rseq_len != rseq_len) + return -EINVAL; + if (current->rseq_sig != sig) + return -EPERM; + /* Already registered. */ + return -EBUSY; + } + + /* + * If there was no rseq previously registered, + * ensure the provided rseq is properly aligned and valid. + */ + if (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) || + rseq_len != sizeof(*rseq)) + return -EINVAL; + if (!access_ok(VERIFY_WRITE, rseq, rseq_len)) + return -EFAULT; + current->rseq = rseq; + current->rseq_len = rseq_len; + current->rseq_sig = sig; + /* + * If rseq was previously inactive, and has just been + * registered, ensure the cpu_id_start and cpu_id fields + * are updated before returning to user-space. + */ + rseq_set_notify_resume(current); + + return 0; +} diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index d9a02b318108..7fe183404c38 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -20,7 +20,7 @@ obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle.o fair.o rt.o deadline.o obj-y += wait.o wait_bit.o swait.o completion.o -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o +obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index 10c83e73837a..e3e3b979f9bd 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -53,6 +53,7 @@ * */ #include "sched.h" +#include <linux/sched_clock.h> /* * Scheduler clock - returns current time in nanosec units. @@ -66,12 +67,7 @@ unsigned long long __weak sched_clock(void) } EXPORT_SYMBOL_GPL(sched_clock); -__read_mostly int sched_clock_running; - -void sched_clock_init(void) -{ - sched_clock_running = 1; -} +static DEFINE_STATIC_KEY_FALSE(sched_clock_running); #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK /* @@ -195,17 +191,40 @@ void clear_sched_clock_stable(void) smp_mb(); /* matches sched_clock_init_late() */ - if (sched_clock_running == 2) + if (static_key_count(&sched_clock_running.key) == 2) __clear_sched_clock_stable(); } +static void __sched_clock_gtod_offset(void) +{ + struct sched_clock_data *scd = this_scd(); + + __scd_stamp(scd); + __gtod_offset = (scd->tick_raw + __sched_clock_offset) - scd->tick_gtod; +} + +void __init sched_clock_init(void) +{ + /* + * Set __gtod_offset such that once we mark sched_clock_running, + * sched_clock_tick() continues where sched_clock() left off. + * + * Even if TSC is buggered, we're still UP at this point so it + * can't really be out of sync. + */ + local_irq_disable(); + __sched_clock_gtod_offset(); + local_irq_enable(); + + static_branch_inc(&sched_clock_running); +} /* * We run this as late_initcall() such that it runs after all built-in drivers, * notably: acpi_processor and intel_idle, which can mark the TSC as unstable. */ static int __init sched_clock_init_late(void) { - sched_clock_running = 2; + static_branch_inc(&sched_clock_running); /* * Ensure that it is impossible to not do a static_key update. * @@ -350,8 +369,8 @@ u64 sched_clock_cpu(int cpu) if (sched_clock_stable()) return sched_clock() + __sched_clock_offset; - if (unlikely(!sched_clock_running)) - return 0ull; + if (!static_branch_unlikely(&sched_clock_running)) + return sched_clock(); preempt_disable_notrace(); scd = cpu_sdc(cpu); @@ -373,7 +392,7 @@ void sched_clock_tick(void) if (sched_clock_stable()) return; - if (unlikely(!sched_clock_running)) + if (!static_branch_unlikely(&sched_clock_running)) return; lockdep_assert_irqs_disabled(); @@ -385,8 +404,6 @@ void sched_clock_tick(void) void sched_clock_tick_stable(void) { - u64 gtod, clock; - if (!sched_clock_stable()) return; @@ -398,9 +415,7 @@ void sched_clock_tick_stable(void) * TSC to be unstable, any computation will be computing crap. */ local_irq_disable(); - gtod = ktime_get_ns(); - clock = sched_clock(); - __gtod_offset = (clock + __sched_clock_offset) - gtod; + __sched_clock_gtod_offset(); local_irq_enable(); } @@ -434,9 +449,17 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ +void __init sched_clock_init(void) +{ + static_branch_inc(&sched_clock_running); + local_irq_disable(); + generic_sched_clock_init(); + local_irq_enable(); +} + u64 sched_clock_cpu(int cpu) { - if (unlikely(!sched_clock_running)) + if (!static_branch_unlikely(&sched_clock_running)) return 0; return sched_clock(); diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index e426b0cb9ac6..a1ad5b7d5521 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -22,8 +22,8 @@ * * See also complete_all(), wait_for_completion() and related routines. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void complete(struct completion *x) { @@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete); * * This will wake up all threads waiting on this particular completion event. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. * * Since complete_all() sets the completion of @x permanently to done * to allow multiple waiters to finish, a call to reinit_completion() diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e9866f86f304..454adf9f8180 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7,15 +7,18 @@ */ #include "sched.h" -#include <linux/kthread.h> #include <linux/nospec.h> +#include <linux/kcov.h> + #include <asm/switch_to.h> #include <asm/tlb.h> #include "../workqueue_internal.h" #include "../smpboot.h" +#include "pelt.h" + #define CREATE_TRACE_POINTS #include <trace/events/sched.h> @@ -44,14 +47,6 @@ const_debug unsigned int sysctl_sched_features = const_debug unsigned int sysctl_sched_nr_migrate = 32; /* - * period over which we average the RT time consumption, measured - * in ms. - * - * default: 1s - */ -const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; - -/* * period over which we measure -rt task CPU usage in us. * default: 1s */ @@ -182,9 +177,9 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->clock_task += delta; -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +#ifdef HAVE_SCHED_AVG_IRQ if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) - sched_rt_avg_update(rq, irq_delta + steal); + update_irq_load_avg(rq, irq_delta + steal); #endif } @@ -411,8 +406,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) * its already queued (either by us or someone else) and will get the * wakeup due to that. * - * This cmpxchg() implies a full barrier, which pairs with the write - * barrier implied by the wakeup in wake_up_q(). + * This cmpxchg() executes a full barrier, which pairs with the full + * barrier executed by the wakeup in wake_up_q(). */ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) return; @@ -440,8 +435,8 @@ void wake_up_q(struct wake_q_head *head) task->wake_q.next = NULL; /* - * wake_up_process() implies a wmb() to pair with the queueing - * in wake_q_add() so as not to miss wakeups. + * wake_up_process() executes a full barrier, which pairs with + * the queueing in wake_q_add() so as not to miss wakeups. */ wake_up_process(task); put_task_struct(task); @@ -648,23 +643,6 @@ bool sched_can_stop_tick(struct rq *rq) return true; } #endif /* CONFIG_NO_HZ_FULL */ - -void sched_avg_update(struct rq *rq) -{ - s64 period = sched_avg_period(); - - while ((s64)(rq_clock(rq) - rq->age_stamp) > period) { - /* - * Inline assembly required to prevent the compiler - * optimising this loop into a divmod call. - * See __iter_div_u64_rem() for another example of this. - */ - asm("" : "+rm" (rq->age_stamp)); - rq->age_stamp += period; - rq->rt_avg /= 2; - } -} - #endif /* CONFIG_SMP */ #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ @@ -1191,12 +1169,14 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p); p->se.nr_migrations++; + rseq_migrate(p); perf_event_task_migrate(p); } __set_task_cpu(p, new_cpu); } +#ifdef CONFIG_NUMA_BALANCING static void __migrate_swap_task(struct task_struct *p, int cpu) { if (task_on_rq_queued(p)) { @@ -1278,16 +1258,17 @@ unlock: /* * Cross migrate two tasks */ -int migrate_swap(struct task_struct *cur, struct task_struct *p) +int migrate_swap(struct task_struct *cur, struct task_struct *p, + int target_cpu, int curr_cpu) { struct migration_swap_arg arg; int ret = -EINVAL; arg = (struct migration_swap_arg){ .src_task = cur, - .src_cpu = task_cpu(cur), + .src_cpu = curr_cpu, .dst_task = p, - .dst_cpu = task_cpu(p), + .dst_cpu = target_cpu, }; if (arg.src_cpu == arg.dst_cpu) @@ -1312,6 +1293,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p) out: return ret; } +#endif /* CONFIG_NUMA_BALANCING */ /* * wait_task_inactive - wait for a thread to unschedule. @@ -1877,8 +1859,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * rq(c1)->lock (if not at the same time, then in that order). * C) LOCK of the rq(c1)->lock scheduling in task * - * Transitivity guarantees that B happens after A and C after B. - * Note: we only require RCpc transitivity. + * Release/acquire chaining guarantees that B happens after A and C after B. * Note: the CPU doing B need not be c0 or c1 * * Example: @@ -1940,16 +1921,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * UNLOCK rq(0)->lock * * - * However; for wakeups there is a second guarantee we must provide, namely we - * must observe the state that lead to our wakeup. That is, not only must our - * task observe its own prior state, it must also observe the stores prior to - * its wakeup. - * - * This means that any means of doing remote wakeups must order the CPU doing - * the wakeup against the CPU the task is going to end up running on. This, - * however, is already required for the regular Program-Order guarantee above, - * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire). - * + * However, for wakeups there is a second guarantee we must provide, namely we + * must ensure that CONDITION=1 done by the caller can not be reordered with + * accesses to the task state; see try_to_wake_up() and set_current_state(). */ /** @@ -1965,6 +1939,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * Atomic against schedule() which would dequeue a task, also see * set_current_state(). * + * This function executes a full memory barrier before accessing the task + * state; see set_current_state(). + * * Return: %true if @p->state changes (an actual wakeup was done), * %false otherwise. */ @@ -1996,21 +1973,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * be possible to, falsely, observe p->on_rq == 0 and get stuck * in smp_cond_load_acquire() below. * - * sched_ttwu_pending() try_to_wake_up() - * [S] p->on_rq = 1; [L] P->state - * UNLOCK rq->lock -----. - * \ - * +--- RMB - * schedule() / - * LOCK rq->lock -----' - * UNLOCK rq->lock + * sched_ttwu_pending() try_to_wake_up() + * STORE p->on_rq = 1 LOAD p->state + * UNLOCK rq->lock + * + * __schedule() (switch to task 'p') + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * UNLOCK rq->lock * * [task p] - * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq + * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq * - * Pairs with the UNLOCK+LOCK on rq->lock from the - * last wakeup of our task and the schedule that got our task - * current. + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). */ smp_rmb(); if (p->on_rq && ttwu_remote(p, wake_flags)) @@ -2024,15 +2000,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * One must be running (->on_cpu == 1) in order to remove oneself * from the runqueue. * - * [S] ->on_cpu = 1; [L] ->on_rq - * UNLOCK rq->lock - * RMB - * LOCK rq->lock - * [S] ->on_rq = 0; [L] ->on_cpu + * __schedule() (switch to task 'p') try_to_wake_up() + * STORE p->on_cpu = 1 LOAD p->on_rq + * UNLOCK rq->lock * - * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock - * from the consecutive calls to schedule(); the first switching to our - * task, the second putting it to sleep. + * __schedule() (put 'p' to sleep) + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * STORE p->on_rq = 0 LOAD p->on_cpu + * + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). */ smp_rmb(); @@ -2138,8 +2116,7 @@ out: * * Return: 1 if the process was woken up, 0 if it was already running. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * This function executes a full memory barrier before accessing the task state. */ int wake_up_process(struct task_struct *p) { @@ -2315,7 +2292,6 @@ static inline void init_schedstats(void) {} int sched_fork(unsigned long clone_flags, struct task_struct *p) { unsigned long flags; - int cpu = get_cpu(); __sched_fork(clone_flags, p); /* @@ -2351,14 +2327,12 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->sched_reset_on_fork = 0; } - if (dl_prio(p->prio)) { - put_cpu(); + if (dl_prio(p->prio)) return -EAGAIN; - } else if (rt_prio(p->prio)) { + else if (rt_prio(p->prio)) p->sched_class = &rt_sched_class; - } else { + else p->sched_class = &fair_sched_class; - } init_entity_runnable_average(&p->se); @@ -2374,7 +2348,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) * We're setting the CPU for the first time, we don't migrate, * so use __set_task_cpu(). */ - __set_task_cpu(p, cpu); + __set_task_cpu(p, smp_processor_id()); if (p->sched_class->task_fork) p->sched_class->task_fork(p); raw_spin_unlock_irqrestore(&p->pi_lock, flags); @@ -2391,8 +2365,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) plist_node_init(&p->pushable_tasks, MAX_PRIO); RB_CLEAR_NODE(&p->pushable_dl_tasks); #endif - - put_cpu(); return 0; } @@ -2632,8 +2604,10 @@ static inline void prepare_task_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { + kcov_prepare_switch(prev); sched_info_switch(rq, prev, next); perf_event_task_sched_out(prev, next); + rseq_preempt(prev); fire_sched_out_preempt_notifiers(prev, next); prepare_task(next); prepare_arch_switch(next); @@ -2700,6 +2674,7 @@ static struct rq *finish_task_switch(struct task_struct *prev) finish_task(prev); finish_lock_switch(rq); finish_arch_post_lock_switch(); + kcov_finish_switch(current); fire_sched_in_preempt_notifiers(current); /* @@ -2718,28 +2693,20 @@ static struct rq *finish_task_switch(struct task_struct *prev) membarrier_mm_sync_core_before_usermode(mm); mmdrop(mm); } - if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) { - switch (prev_state) { - case TASK_DEAD: - if (prev->sched_class->task_dead) - prev->sched_class->task_dead(prev); + if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); - /* - * Remove function-return probe instances associated with this - * task and put them back on the free list. - */ - kprobe_flush_task(prev); + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); - /* Task is done with its stack. */ - put_task_stack(prev); + /* Task is done with its stack. */ + put_task_stack(prev); - put_task_struct(prev); - break; - - case TASK_PARKED: - kthread_park_complete(prev); - break; - } + put_task_struct(prev); } tick_nohz_task_switch(); @@ -3107,7 +3074,9 @@ static void sched_tick_remote(struct work_struct *work) struct tick_work *twork = container_of(dwork, struct tick_work, work); int cpu = twork->cpu; struct rq *rq = cpu_rq(cpu); + struct task_struct *curr; struct rq_flags rf; + u64 delta; /* * Handle the tick only if it appears the remote CPU is running in full @@ -3116,25 +3085,29 @@ static void sched_tick_remote(struct work_struct *work) * statistics and checks timeslices in a time-independent way, regardless * of when exactly it is running. */ - if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) { - struct task_struct *curr; - u64 delta; + if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu)) + goto out_requeue; - rq_lock_irq(rq, &rf); - update_rq_clock(rq); - curr = rq->curr; - delta = rq_clock_task(rq) - curr->se.exec_start; + rq_lock_irq(rq, &rf); + curr = rq->curr; + if (is_idle_task(curr)) + goto out_unlock; - /* - * Make sure the next tick runs within a reasonable - * amount of time. - */ - WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); - curr->sched_class->task_tick(rq, curr, 0); - rq_unlock_irq(rq, &rf); - } + update_rq_clock(rq); + delta = rq_clock_task(rq) - curr->se.exec_start; /* + * Make sure the next tick runs within a reasonable + * amount of time. + */ + WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + curr->sched_class->task_tick(rq, curr, 0); + +out_unlock: + rq_unlock_irq(rq, &rf); + +out_requeue: + /* * Run the remote tick once per second (1Hz). This arbitrary * frequency is large enough to avoid overload but short enough * to keep scheduler internal stats reasonably up to date. @@ -5711,13 +5684,6 @@ void set_rq_offline(struct rq *rq) } } -static void set_cpu_rq_start_time(unsigned int cpu) -{ - struct rq *rq = cpu_rq(cpu); - - rq->age_stamp = sched_clock_cpu(cpu); -} - /* * used to mark begin/end of suspend/resume: */ @@ -5771,6 +5737,18 @@ int sched_cpu_activate(unsigned int cpu) struct rq *rq = cpu_rq(cpu); struct rq_flags rf; +#ifdef CONFIG_SCHED_SMT + /* + * The sched_smt_present static key needs to be evaluated on every + * hotplug event because at boot time SMT might be disabled when + * the number of booted CPUs is limited. + * + * If then later a sibling gets hotplugged, then the key would stay + * off and SMT scheduling would never be functional. + */ + if (cpumask_weight(cpu_smt_mask(cpu)) > 1) + static_branch_enable_cpuslocked(&sched_smt_present); +#endif set_cpu_active(cpu, true); if (sched_smp_initialized) { @@ -5835,7 +5813,6 @@ static void sched_rq_cpu_starting(unsigned int cpu) int sched_cpu_starting(unsigned int cpu) { - set_cpu_rq_start_time(cpu); sched_rq_cpu_starting(cpu); sched_tick_start(cpu); return 0; @@ -5868,22 +5845,6 @@ int sched_cpu_dying(unsigned int cpu) } #endif -#ifdef CONFIG_SCHED_SMT -DEFINE_STATIC_KEY_FALSE(sched_smt_present); - -static void sched_init_smt(void) -{ - /* - * We've enumerated all CPUs and will assume that if any CPU - * has SMT siblings, CPU0 will too. - */ - if (cpumask_weight(cpu_smt_mask(0)) > 1) - static_branch_enable(&sched_smt_present); -} -#else -static inline void sched_init_smt(void) { } -#endif - void __init sched_init_smp(void) { sched_init_numa(); @@ -5905,8 +5866,6 @@ void __init sched_init_smp(void) init_sched_rt_class(); init_sched_dl_class(); - sched_init_smt(); - sched_smp_initialized = true; } @@ -5951,7 +5910,6 @@ void __init sched_init(void) int i, j; unsigned long alloc_size = 0, ptr; - sched_clock_init(); wait_bit_init(); #ifdef CONFIG_FAIR_GROUP_SCHED @@ -6103,7 +6061,6 @@ void __init sched_init(void) #ifdef CONFIG_SMP idle_thread_set_boot_cpu(); - set_cpu_rq_start_time(smp_processor_id()); #endif init_sched_fair_class(); @@ -6782,6 +6739,16 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v) seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled); seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time); + if (schedstat_enabled() && tg != &root_task_group) { + u64 ws = 0; + int i; + + for_each_possible_cpu(i) + ws += schedstat_val(tg->se[i]->statistics.wait_sum); + + seq_printf(sf, "wait_sum %llu\n", ws); + } + return 0; } #endif /* CONFIG_CFS_BANDWIDTH */ diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 3cde46483f0a..3fffad3bc8a8 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -53,9 +53,7 @@ struct sugov_cpu { unsigned int iowait_boost_max; u64 last_update; - /* The fields below are only needed when sharing a policy: */ - unsigned long util_cfs; - unsigned long util_dl; + unsigned long bw_dl; unsigned long max; /* The field below is for single-CPU policies only: */ @@ -179,33 +177,90 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, return cpufreq_driver_resolve_freq(policy, freq); } -static void sugov_get_util(struct sugov_cpu *sg_cpu) +/* + * This function computes an effective utilization for the given CPU, to be + * used for frequency selection given the linear relation: f = u * f_max. + * + * The scheduler tracks the following metrics: + * + * cpu_util_{cfs,rt,dl,irq}() + * cpu_bw_dl() + * + * Where the cfs,rt and dl util numbers are tracked with the same metric and + * synchronized windows and are thus directly comparable. + * + * The cfs,rt,dl utilization are the running times measured with rq->clock_task + * which excludes things like IRQ and steal-time. These latter are then accrued + * in the irq utilization. + * + * The DL bandwidth number otoh is not a measured metric but a value computed + * based on the task model parameters and gives the minimal utilization + * required to meet deadlines. + */ +static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); + unsigned long util, irq, max; - sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); - sg_cpu->util_cfs = cpu_util_cfs(rq); - sg_cpu->util_dl = cpu_util_dl(rq); -} + sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); + sg_cpu->bw_dl = cpu_bw_dl(rq); -static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu) -{ - struct rq *rq = cpu_rq(sg_cpu->cpu); + if (rt_rq_is_runnable(&rq->rt)) + return max; - if (rq->rt.rt_nr_running) - return sg_cpu->max; + /* + * Early check to see if IRQ/steal time saturates the CPU, can be + * because of inaccuracies in how we track these -- see + * update_irq_load_avg(). + */ + irq = cpu_util_irq(rq); + if (unlikely(irq >= max)) + return max; + + /* + * Because the time spend on RT/DL tasks is visible as 'lost' time to + * CFS tasks and we use the same metric to track the effective + * utilization (PELT windows are synchronized) we can directly add them + * to obtain the CPU's actual utilization. + */ + util = cpu_util_cfs(rq); + util += cpu_util_rt(rq); + + /* + * We do not make cpu_util_dl() a permanent part of this sum because we + * want to use cpu_bw_dl() later on, but we need to check if the + * CFS+RT+DL sum is saturated (ie. no idle time) such that we select + * f_max when there is no idle time. + * + * NOTE: numerical errors or stop class might cause us to not quite hit + * saturation when we should -- something for later. + */ + if ((util + cpu_util_dl(rq)) >= max) + return max; + + /* + * There is still idle time; further improve the number by using the + * irq metric. Because IRQ/steal time is hidden from the task clock we + * need to scale the task numbers: + * + * 1 - irq + * U' = irq + ------- * U + * max + */ + util = scale_irq_capacity(util, irq, max); + util += irq; /* - * Utilization required by DEADLINE must always be granted while, for - * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to - * gracefully reduce the frequency when no tasks show up for longer + * Bandwidth required by DEADLINE must always be granted while, for + * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism + * to gracefully reduce the frequency when no tasks show up for longer * periods of time. * - * Ideally we would like to set util_dl as min/guaranteed freq and - * util_cfs + util_dl as requested freq. However, cpufreq is not yet - * ready for such an interface. So, we only do the latter for now. + * Ideally we would like to set bw_dl as min/guaranteed freq and util + + * bw_dl as requested freq. However, cpufreq is not yet ready for such + * an interface. So, we only do the latter for now. */ - return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs)); + return min(max, util + sg_cpu->bw_dl); } /** @@ -360,7 +415,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } */ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy) { - if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl) + if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl) sg_policy->need_freq_update = true; } @@ -383,9 +438,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, busy = sugov_cpu_is_busy(sg_cpu); - sugov_get_util(sg_cpu); + util = sugov_get_util(sg_cpu); max = sg_cpu->max; - util = sugov_aggregate_util(sg_cpu); sugov_iowait_apply(sg_cpu, time, &util, &max); next_f = get_next_freq(sg_policy, util, max); /* @@ -424,9 +478,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); unsigned long j_util, j_max; - sugov_get_util(j_sg_cpu); + j_util = sugov_get_util(j_sg_cpu); j_max = j_sg_cpu->max; - j_util = sugov_aggregate_util(j_sg_cpu); sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max); if (j_util * max > j_max * util) { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fbfc3f1d368a..997ea7b839fa 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,7 @@ * Fabio Checconi <fchecconi@gmail.com> */ #include "sched.h" +#include "pelt.h" struct dl_bandwidth def_dl_bandwidth; @@ -1179,8 +1180,6 @@ static void update_curr_dl(struct rq *rq) curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); - sched_rt_avg_update(rq, delta_exec); - if (dl_entity_is_special(dl_se)) return; @@ -1761,6 +1760,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) deadline_queue_push_tasks(rq); + if (rq->curr->sched_class != &dl_sched_class) + update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + return p; } @@ -1768,6 +1770,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -1784,6 +1787,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) { update_curr_dl(rq); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); /* * Even when we have runtime, update_curr_dl() might have resulted in us * not being the leftmost task anymore. In that case NEED_RESCHED will @@ -2090,8 +2094,14 @@ retry: sub_rq_bw(&next_task->dl, &rq->dl); set_task_cpu(next_task, later_rq->cpu); add_rq_bw(&next_task->dl, &later_rq->dl); + + /* + * Update the later_rq clock here, because the clock is used + * by the cpufreq_update_util() inside __add_running_bw(). + */ + update_rq_clock(later_rq); add_running_bw(&next_task->dl, &later_rq->dl); - activate_task(later_rq, next_task, 0); + activate_task(later_rq, next_task, ENQUEUE_NOCLOCK); ret = 1; resched_curr(later_rq); @@ -2290,8 +2300,17 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && p->dl.dl_runtime) task_non_contending(p); - if (!task_on_rq_queued(p)) + if (!task_on_rq_queued(p)) { + /* + * Inactive timer is armed. However, p is leaving DEADLINE and + * might migrate away from this rq while continuing to run on + * some other class. We need to remove its contribution from + * this rq running_bw now, or sub_rq_bw (below) will complain. + */ + if (p->dl.dl_non_contending) + sub_running_bw(&p->dl, &rq->dl); sub_rq_bw(&p->dl, &rq->dl); + } /* * We cannot use inactive_task_timer() to invoke sub_running_bw() diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index e593b4118578..60caf1fb94e0 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -111,20 +111,19 @@ static int sched_feat_set(char *cmp) cmp += 3; } - for (i = 0; i < __SCHED_FEAT_NR; i++) { - if (strcmp(cmp, sched_feat_names[i]) == 0) { - if (neg) { - sysctl_sched_features &= ~(1UL << i); - sched_feat_disable(i); - } else { - sysctl_sched_features |= (1UL << i); - sched_feat_enable(i); - } - break; - } + i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp); + if (i < 0) + return i; + + if (neg) { + sysctl_sched_features &= ~(1UL << i); + sched_feat_disable(i); + } else { + sysctl_sched_features |= (1UL << i); + sched_feat_enable(i); } - return i; + return 0; } static ssize_t @@ -133,7 +132,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, { char buf[64]; char *cmp; - int i; + int ret; struct inode *inode; if (cnt > 63) @@ -148,10 +147,10 @@ sched_feat_write(struct file *filp, const char __user *ubuf, /* Ensure the static_key remains in a consistent state */ inode = file_inode(filp); inode_lock(inode); - i = sched_feat_set(cmp); + ret = sched_feat_set(cmp); inode_unlock(inode); - if (i == __SCHED_FEAT_NR) - return -EINVAL; + if (ret < 0) + return ret; *ppos += cnt; @@ -623,8 +622,6 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) #undef PU } -extern __read_mostly int sched_clock_running; - static void print_cpu(struct seq_file *m, int cpu) { struct rq *rq = cpu_rq(cpu); @@ -843,8 +840,8 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf, unsigned long tpf, unsigned long gsf, unsigned long gpf) { SEQ_printf(m, "numa_faults node=%d ", node); - SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf); - SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf); + SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf); + SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf); } #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e497c05aab7f..b39fb596f6c1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -255,9 +255,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq) return cfs_rq->rq; } -/* An entity is a task if it doesn't "own" a runqueue */ -#define entity_is_task(se) (!se->my_q) - static inline struct task_struct *task_of(struct sched_entity *se) { SCHED_WARN_ON(!entity_is_task(se)); @@ -419,7 +416,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq) return container_of(cfs_rq, struct rq, cfs); } -#define entity_is_task(se) 1 #define for_each_sched_entity(se) \ for (; se; se = NULL) @@ -692,7 +688,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) } #ifdef CONFIG_SMP - +#include "pelt.h" #include "sched-pelt.h" static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu); @@ -735,11 +731,12 @@ static void attach_entity_cfs_rq(struct sched_entity *se); * To solve this problem, we also cap the util_avg of successive tasks to * only 1/2 of the left utilization budget: * - * util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n + * util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n * - * where n denotes the nth task. + * where n denotes the nth task and cpu_scale the CPU capacity. * - * For example, a simplest series from the beginning would be like: + * For example, for a CPU with 1024 of capacity, a simplest series from + * the beginning would be like: * * task util_avg: 512, 256, 128, 64, 32, 16, 8, ... * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ... @@ -751,7 +748,8 @@ void post_init_entity_util_avg(struct sched_entity *se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); struct sched_avg *sa = &se->avg; - long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2; + long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); + long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2; if (cap > 0) { if (cfs_rq->avg.util_avg != 0) { @@ -1314,7 +1312,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, * of each group. Skip other nodes. */ if (sched_numa_topology_type == NUMA_BACKPLANE && - dist > maxdist) + dist >= maxdist) continue; /* Add up the faults from nearby nodes. */ @@ -1452,15 +1450,12 @@ static unsigned long capacity_of(int cpu); /* Cached statistics for all CPUs within a node */ struct numa_stats { - unsigned long nr_running; unsigned long load; /* Total compute capacity of CPUs on a node */ unsigned long compute_capacity; - /* Approximate capacity in terms of runnable tasks on a node */ - unsigned long task_capacity; - int has_free_capacity; + unsigned int nr_running; }; /* @@ -1487,8 +1482,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid) * the @ns structure is NULL'ed and task_numa_compare() will * not find this node attractive. * - * We'll either bail at !has_free_capacity, or we'll detect a huge - * imbalance and bail there. + * We'll detect a huge imbalance and bail there. */ if (!cpus) return; @@ -1497,9 +1491,8 @@ static void update_numa_stats(struct numa_stats *ns, int nid) smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity); capacity = cpus / smt; /* cores */ - ns->task_capacity = min_t(unsigned, capacity, + capacity = min_t(unsigned, capacity, DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE)); - ns->has_free_capacity = (ns->nr_running < ns->task_capacity); } struct task_numa_env { @@ -1548,28 +1541,12 @@ static bool load_too_imbalanced(long src_load, long dst_load, src_capacity = env->src_stats.compute_capacity; dst_capacity = env->dst_stats.compute_capacity; - /* We care about the slope of the imbalance, not the direction. */ - if (dst_load < src_load) - swap(dst_load, src_load); + imb = abs(dst_load * src_capacity - src_load * dst_capacity); - /* Is the difference below the threshold? */ - imb = dst_load * src_capacity * 100 - - src_load * dst_capacity * env->imbalance_pct; - if (imb <= 0) - return false; - - /* - * The imbalance is above the allowed threshold. - * Compare it with the old imbalance. - */ orig_src_load = env->src_stats.load; orig_dst_load = env->dst_stats.load; - if (orig_dst_load < orig_src_load) - swap(orig_dst_load, orig_src_load); - - old_imb = orig_dst_load * src_capacity * 100 - - orig_src_load * dst_capacity * env->imbalance_pct; + old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity); /* Would this change make things worse? */ return (imb > old_imb); @@ -1582,9 +1559,8 @@ static bool load_too_imbalanced(long src_load, long dst_load, * be exchanged with the source task */ static void task_numa_compare(struct task_numa_env *env, - long taskimp, long groupimp) + long taskimp, long groupimp, bool maymove) { - struct rq *src_rq = cpu_rq(env->src_cpu); struct rq *dst_rq = cpu_rq(env->dst_cpu); struct task_struct *cur; long src_load, dst_load; @@ -1605,97 +1581,73 @@ static void task_numa_compare(struct task_numa_env *env, if (cur == env->p) goto unlock; + if (!cur) { + if (maymove || imp > env->best_imp) + goto assign; + else + goto unlock; + } + /* * "imp" is the fault differential for the source task between the * source and destination node. Calculate the total differential for * the source task and potential destination task. The more negative - * the value is, the more rmeote accesses that would be expected to + * the value is, the more remote accesses that would be expected to * be incurred if the tasks were swapped. */ - if (cur) { - /* Skip this swap candidate if cannot move to the source CPU: */ - if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) - goto unlock; + /* Skip this swap candidate if cannot move to the source cpu */ + if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) + goto unlock; + /* + * If dst and source tasks are in the same NUMA group, or not + * in any group then look only at task weights. + */ + if (cur->numa_group == env->p->numa_group) { + imp = taskimp + task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); /* - * If dst and source tasks are in the same NUMA group, or not - * in any group then look only at task weights. + * Add some hysteresis to prevent swapping the + * tasks within a group over tiny differences. */ - if (cur->numa_group == env->p->numa_group) { - imp = taskimp + task_weight(cur, env->src_nid, dist) - - task_weight(cur, env->dst_nid, dist); - /* - * Add some hysteresis to prevent swapping the - * tasks within a group over tiny differences. - */ - if (cur->numa_group) - imp -= imp/16; - } else { - /* - * Compare the group weights. If a task is all by - * itself (not part of a group), use the task weight - * instead. - */ - if (cur->numa_group) - imp += group_weight(cur, env->src_nid, dist) - - group_weight(cur, env->dst_nid, dist); - else - imp += task_weight(cur, env->src_nid, dist) - - task_weight(cur, env->dst_nid, dist); - } + if (cur->numa_group) + imp -= imp / 16; + } else { + /* + * Compare the group weights. If a task is all by itself + * (not part of a group), use the task weight instead. + */ + if (cur->numa_group && env->p->numa_group) + imp += group_weight(cur, env->src_nid, dist) - + group_weight(cur, env->dst_nid, dist); + else + imp += task_weight(cur, env->src_nid, dist) - + task_weight(cur, env->dst_nid, dist); } - if (imp <= env->best_imp && moveimp <= env->best_imp) + if (imp <= env->best_imp) goto unlock; - if (!cur) { - /* Is there capacity at our destination? */ - if (env->src_stats.nr_running <= env->src_stats.task_capacity && - !env->dst_stats.has_free_capacity) - goto unlock; - - goto balance; - } - - /* Balance doesn't matter much if we're running a task per CPU: */ - if (imp > env->best_imp && src_rq->nr_running == 1 && - dst_rq->nr_running == 1) + if (maymove && moveimp > imp && moveimp > env->best_imp) { + imp = moveimp - 1; + cur = NULL; goto assign; + } /* * In the overloaded case, try and keep the load balanced. */ -balance: - load = task_h_load(env->p); + load = task_h_load(env->p) - task_h_load(cur); + if (!load) + goto assign; + dst_load = env->dst_stats.load + load; src_load = env->src_stats.load - load; - if (moveimp > imp && moveimp > env->best_imp) { - /* - * If the improvement from just moving env->p direction is - * better than swapping tasks around, check if a move is - * possible. Store a slightly smaller score than moveimp, - * so an actually idle CPU will win. - */ - if (!load_too_imbalanced(src_load, dst_load, env)) { - imp = moveimp - 1; - cur = NULL; - goto assign; - } - } - - if (imp <= env->best_imp) - goto unlock; - - if (cur) { - load = task_h_load(cur); - dst_load -= load; - src_load += load; - } - if (load_too_imbalanced(src_load, dst_load, env)) goto unlock; +assign: /* * One idle CPU per node is evaluated for a task numa move. * Call select_idle_sibling to maybe find a better one. @@ -1711,7 +1663,6 @@ balance: local_irq_enable(); } -assign: task_numa_assign(env, cur, imp); unlock: rcu_read_unlock(); @@ -1720,43 +1671,30 @@ unlock: static void task_numa_find_cpu(struct task_numa_env *env, long taskimp, long groupimp) { + long src_load, dst_load, load; + bool maymove = false; int cpu; + load = task_h_load(env->p); + dst_load = env->dst_stats.load + load; + src_load = env->src_stats.load - load; + + /* + * If the improvement from just moving env->p direction is better + * than swapping tasks around, check if a move is possible. + */ + maymove = !load_too_imbalanced(src_load, dst_load, env); + for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { /* Skip this CPU if the source task cannot migrate */ if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed)) continue; env->dst_cpu = cpu; - task_numa_compare(env, taskimp, groupimp); + task_numa_compare(env, taskimp, groupimp, maymove); } } -/* Only move tasks to a NUMA node less busy than the current node. */ -static bool numa_has_capacity(struct task_numa_env *env) -{ - struct numa_stats *src = &env->src_stats; - struct numa_stats *dst = &env->dst_stats; - - if (src->has_free_capacity && !dst->has_free_capacity) - return false; - - /* - * Only consider a task move if the source has a higher load - * than the destination, corrected for CPU capacity on each node. - * - * src->load dst->load - * --------------------- vs --------------------- - * src->compute_capacity dst->compute_capacity - */ - if (src->load * dst->compute_capacity * env->imbalance_pct > - - dst->load * src->compute_capacity * 100) - return true; - - return false; -} - static int task_numa_migrate(struct task_struct *p) { struct task_numa_env env = { @@ -1797,7 +1735,7 @@ static int task_numa_migrate(struct task_struct *p) * elsewhere, so there is no point in (re)trying. */ if (unlikely(!sd)) { - p->numa_preferred_nid = task_node(p); + sched_setnuma(p, task_node(p)); return -EINVAL; } @@ -1811,8 +1749,7 @@ static int task_numa_migrate(struct task_struct *p) update_numa_stats(&env.dst_stats, env.dst_nid); /* Try to find a spot on the preferred nid. */ - if (numa_has_capacity(&env)) - task_numa_find_cpu(&env, taskimp, groupimp); + task_numa_find_cpu(&env, taskimp, groupimp); /* * Look at other nodes in these cases: @@ -1842,8 +1779,7 @@ static int task_numa_migrate(struct task_struct *p) env.dist = dist; env.dst_nid = nid; update_numa_stats(&env.dst_stats, env.dst_nid); - if (numa_has_capacity(&env)) - task_numa_find_cpu(&env, taskimp, groupimp); + task_numa_find_cpu(&env, taskimp, groupimp); } } @@ -1856,15 +1792,13 @@ static int task_numa_migrate(struct task_struct *p) * trying for a better one later. Do not set the preferred node here. */ if (p->numa_group) { - struct numa_group *ng = p->numa_group; - if (env.best_cpu == -1) nid = env.src_nid; else - nid = env.dst_nid; + nid = cpu_to_node(env.best_cpu); - if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng)) - sched_setnuma(p, env.dst_nid); + if (nid != p->numa_preferred_nid) + sched_setnuma(p, nid); } /* No better CPU than the current one was found. */ @@ -1884,7 +1818,8 @@ static int task_numa_migrate(struct task_struct *p) return ret; } - ret = migrate_swap(p, env.best_task); + ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu); + if (ret != 0) trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); put_task_struct(env.best_task); @@ -2144,8 +2079,8 @@ static int preferred_group_nid(struct task_struct *p, int nid) static void task_numa_placement(struct task_struct *p) { - int seq, nid, max_nid = -1, max_group_nid = -1; - unsigned long max_faults = 0, max_group_faults = 0; + int seq, nid, max_nid = -1; + unsigned long max_faults = 0; unsigned long fault_types[2] = { 0, 0 }; unsigned long total_faults; u64 runtime, period; @@ -2224,33 +2159,30 @@ static void task_numa_placement(struct task_struct *p) } } - if (faults > max_faults) { - max_faults = faults; + if (!p->numa_group) { + if (faults > max_faults) { + max_faults = faults; + max_nid = nid; + } + } else if (group_faults > max_faults) { + max_faults = group_faults; max_nid = nid; } - - if (group_faults > max_group_faults) { - max_group_faults = group_faults; - max_group_nid = nid; - } } - update_task_scan_period(p, fault_types[0], fault_types[1]); - if (p->numa_group) { numa_group_count_active_nodes(p->numa_group); spin_unlock_irq(group_lock); - max_nid = preferred_group_nid(p, max_group_nid); + max_nid = preferred_group_nid(p, max_nid); } if (max_faults) { /* Set the new preferred node */ if (max_nid != p->numa_preferred_nid) sched_setnuma(p, max_nid); - - if (task_node(p) != p->numa_preferred_nid) - numa_migrate_preferred(p); } + + update_task_scan_period(p, fault_types[0], fault_types[1]); } static inline int get_numa_group(struct numa_group *grp) @@ -2450,14 +2382,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) numa_is_active_node(mem_node, ng)) local = 1; - task_numa_placement(p); - /* * Retry task to preferred node migration periodically, in case it * case it previously failed, or the scheduler moved us. */ - if (time_after(jiffies, p->numa_migrate_retry)) + if (time_after(jiffies, p->numa_migrate_retry)) { + task_numa_placement(p); numa_migrate_preferred(p); + } if (migrated) p->numa_pages_migrated += pages; @@ -2749,19 +2681,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) } while (0) #ifdef CONFIG_SMP -/* - * XXX we want to get rid of these helpers and use the full load resolution. - */ -static inline long se_weight(struct sched_entity *se) -{ - return scale_load_down(se->load.weight); -} - -static inline long se_runnable(struct sched_entity *se) -{ - return scale_load_down(se->runnable_weight); -} - static inline void enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { @@ -3062,314 +2981,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) } #ifdef CONFIG_SMP -/* - * Approximate: - * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) - */ -static u64 decay_load(u64 val, u64 n) -{ - unsigned int local_n; - - if (unlikely(n > LOAD_AVG_PERIOD * 63)) - return 0; - - /* after bounds checking we can collapse to 32-bit */ - local_n = n; - - /* - * As y^PERIOD = 1/2, we can combine - * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD) - * With a look-up table which covers y^n (n<PERIOD) - * - * To achieve constant time decay_load. - */ - if (unlikely(local_n >= LOAD_AVG_PERIOD)) { - val >>= local_n / LOAD_AVG_PERIOD; - local_n %= LOAD_AVG_PERIOD; - } - - val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32); - return val; -} - -static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) -{ - u32 c1, c2, c3 = d3; /* y^0 == 1 */ - - /* - * c1 = d1 y^p - */ - c1 = decay_load((u64)d1, periods); - - /* - * p-1 - * c2 = 1024 \Sum y^n - * n=1 - * - * inf inf - * = 1024 ( \Sum y^n - \Sum y^n - y^0 ) - * n=0 n=p - */ - c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024; - - return c1 + c2 + c3; -} - -/* - * Accumulate the three separate parts of the sum; d1 the remainder - * of the last (incomplete) period, d2 the span of full periods and d3 - * the remainder of the (incomplete) current period. - * - * d1 d2 d3 - * ^ ^ ^ - * | | | - * |<->|<----------------->|<--->| - * ... |---x---|------| ... |------|-----x (now) - * - * p-1 - * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0 - * n=1 - * - * = u y^p + (Step 1) - * - * p-1 - * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2) - * n=1 - */ -static __always_inline u32 -accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, - unsigned long load, unsigned long runnable, int running) -{ - unsigned long scale_freq, scale_cpu; - u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ - u64 periods; - - scale_freq = arch_scale_freq_capacity(cpu); - scale_cpu = arch_scale_cpu_capacity(NULL, cpu); - - delta += sa->period_contrib; - periods = delta / 1024; /* A period is 1024us (~1ms) */ - - /* - * Step 1: decay old *_sum if we crossed period boundaries. - */ - if (periods) { - sa->load_sum = decay_load(sa->load_sum, periods); - sa->runnable_load_sum = - decay_load(sa->runnable_load_sum, periods); - sa->util_sum = decay_load((u64)(sa->util_sum), periods); - - /* - * Step 2 - */ - delta %= 1024; - contrib = __accumulate_pelt_segments(periods, - 1024 - sa->period_contrib, delta); - } - sa->period_contrib = delta; - - contrib = cap_scale(contrib, scale_freq); - if (load) - sa->load_sum += load * contrib; - if (runnable) - sa->runnable_load_sum += runnable * contrib; - if (running) - sa->util_sum += contrib * scale_cpu; - - return periods; -} - -/* - * We can represent the historical contribution to runnable average as the - * coefficients of a geometric series. To do this we sub-divide our runnable - * history into segments of approximately 1ms (1024us); label the segment that - * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g. - * - * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ... - * p0 p1 p2 - * (now) (~1ms ago) (~2ms ago) - * - * Let u_i denote the fraction of p_i that the entity was runnable. - * - * We then designate the fractions u_i as our co-efficients, yielding the - * following representation of historical load: - * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ... - * - * We choose y based on the with of a reasonably scheduling period, fixing: - * y^32 = 0.5 - * - * This means that the contribution to load ~32ms ago (u_32) will be weighted - * approximately half as much as the contribution to load within the last ms - * (u_0). - * - * When a period "rolls over" and we have new u_0`, multiplying the previous - * sum again by y is sufficient to update: - * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) - * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] - */ -static __always_inline int -___update_load_sum(u64 now, int cpu, struct sched_avg *sa, - unsigned long load, unsigned long runnable, int running) -{ - u64 delta; - - delta = now - sa->last_update_time; - /* - * This should only happen when time goes backwards, which it - * unfortunately does during sched clock init when we swap over to TSC. - */ - if ((s64)delta < 0) { - sa->last_update_time = now; - return 0; - } - - /* - * Use 1024ns as the unit of measurement since it's a reasonable - * approximation of 1us and fast to compute. - */ - delta >>= 10; - if (!delta) - return 0; - - sa->last_update_time += delta << 10; - - /* - * running is a subset of runnable (weight) so running can't be set if - * runnable is clear. But there are some corner cases where the current - * se has been already dequeued but cfs_rq->curr still points to it. - * This means that weight will be 0 but not running for a sched_entity - * but also for a cfs_rq if the latter becomes idle. As an example, - * this happens during idle_balance() which calls - * update_blocked_averages() - */ - if (!load) - runnable = running = 0; - - /* - * Now we know we crossed measurement unit boundaries. The *_avg - * accrues by two steps: - * - * Step 1: accumulate *_sum since last_update_time. If we haven't - * crossed period boundaries, finish. - */ - if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) - return 0; - - return 1; -} - -static __always_inline void -___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable) -{ - u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib; - - /* - * Step 2: update *_avg. - */ - sa->load_avg = div_u64(load * sa->load_sum, divider); - sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider); - sa->util_avg = sa->util_sum / divider; -} - -/* - * When a task is dequeued, its estimated utilization should not be update if - * its util_avg has not been updated at least once. - * This flag is used to synchronize util_avg updates with util_est updates. - * We map this information into the LSB bit of the utilization saved at - * dequeue time (i.e. util_est.dequeued). - */ -#define UTIL_AVG_UNCHANGED 0x1 - -static inline void cfs_se_util_change(struct sched_avg *avg) -{ - unsigned int enqueued; - - if (!sched_feat(UTIL_EST)) - return; - - /* Avoid store if the flag has been already set */ - enqueued = avg->util_est.enqueued; - if (!(enqueued & UTIL_AVG_UNCHANGED)) - return; - - /* Reset flag to report util_avg has been updated */ - enqueued &= ~UTIL_AVG_UNCHANGED; - WRITE_ONCE(avg->util_est.enqueued, enqueued); -} - -/* - * sched_entity: - * - * task: - * se_runnable() == se_weight() - * - * group: [ see update_cfs_group() ] - * se_weight() = tg->weight * grq->load_avg / tg->load_avg - * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg - * - * load_sum := runnable_sum - * load_avg = se_weight(se) * runnable_avg - * - * runnable_load_sum := runnable_sum - * runnable_load_avg = se_runnable(se) * runnable_avg - * - * XXX collapse load_sum and runnable_load_sum - * - * cfq_rs: - * - * load_sum = \Sum se_weight(se) * se->avg.load_sum - * load_avg = \Sum se->avg.load_avg - * - * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum - * runnable_load_avg = \Sum se->avg.runable_load_avg - */ - -static int -__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) -{ - if (entity_is_task(se)) - se->runnable_weight = se->load.weight; - - if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { - ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); - return 1; - } - - return 0; -} - -static int -__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - if (entity_is_task(se)) - se->runnable_weight = se->load.weight; - - if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, - cfs_rq->curr == se)) { - - ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); - cfs_se_util_change(&se->avg); - return 1; - } - - return 0; -} - -static int -__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) -{ - if (___update_load_sum(now, cpu, &cfs_rq->avg, - scale_load_down(cfs_rq->load.weight), - scale_load_down(cfs_rq->runnable_weight), - cfs_rq->curr != NULL)) { - - ___update_load_avg(&cfs_rq->avg, 1, 1); - return 1; - } - - return 0; -} - #ifdef CONFIG_FAIR_GROUP_SCHED /** * update_tg_load_avg - update the tg's load avg @@ -3982,18 +3593,10 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) if (!sched_feat(UTIL_EST)) return; - /* - * Update root cfs_rq's estimated utilization - * - * If *p is the last task then the root cfs_rq's estimated utilization - * of a CPU is 0 by definition. - */ - ue.enqueued = 0; - if (cfs_rq->nr_running) { - ue.enqueued = cfs_rq->avg.util_est.enqueued; - ue.enqueued -= min_t(unsigned int, ue.enqueued, - (_task_util_est(p) | UTIL_AVG_UNCHANGED)); - } + /* Update root cfs_rq's estimated utilization */ + ue.enqueued = cfs_rq->avg.util_est.enqueued; + ue.enqueued -= min_t(unsigned int, ue.enqueued, + (_task_util_est(p) | UTIL_AVG_UNCHANGED)); WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued); /* @@ -4045,12 +3648,6 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) #else /* CONFIG_SMP */ -static inline int -update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) -{ - return 0; -} - #define UPDATE_TG 0x0 #define SKIP_AGE_LOAD 0x0 #define DO_ATTACH 0x0 @@ -4590,6 +4187,7 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) now = sched_clock_cpu(smp_processor_id()); cfs_b->runtime = cfs_b->quota; cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); + cfs_b->expires_seq++; } static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) @@ -4612,6 +4210,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) struct task_group *tg = cfs_rq->tg; struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); u64 amount = 0, min_amount, expires; + int expires_seq; /* note: this is a positive sum as runtime_remaining <= 0 */ min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; @@ -4628,6 +4227,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) cfs_b->idle = 0; } } + expires_seq = cfs_b->expires_seq; expires = cfs_b->runtime_expires; raw_spin_unlock(&cfs_b->lock); @@ -4637,8 +4237,10 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) * spread between our sched_clock and the one on which runtime was * issued. */ - if ((s64)(expires - cfs_rq->runtime_expires) > 0) + if (cfs_rq->expires_seq != expires_seq) { + cfs_rq->expires_seq = expires_seq; cfs_rq->runtime_expires = expires; + } return cfs_rq->runtime_remaining > 0; } @@ -4664,12 +4266,9 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) * has not truly expired. * * Fortunately we can check determine whether this the case by checking - * whether the global deadline has advanced. It is valid to compare - * cfs_b->runtime_expires without any locks since we only care about - * exact equality, so a partial write will still work. + * whether the global deadline(cfs_b->expires_seq) has advanced. */ - - if (cfs_rq->runtime_expires != cfs_b->runtime_expires) { + if (cfs_rq->expires_seq == cfs_b->expires_seq) { /* extend local deadline, drift is bounded above by 2 ticks */ cfs_rq->runtime_expires += TICK_NSEC; } else { @@ -4732,7 +4331,6 @@ static inline int throttled_lb_pair(struct task_group *tg, throttled_hierarchy(dest_cfs_rq); } -/* updated child weight may affect parent so we have to do this bottom up */ static int tg_unthrottle_up(struct task_group *tg, void *data) { struct rq *rq = data; @@ -5202,13 +4800,18 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) { + u64 overrun; + lockdep_assert_held(&cfs_b->lock); - if (!cfs_b->period_active) { - cfs_b->period_active = 1; - hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); - hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); - } + if (cfs_b->period_active) + return; + + cfs_b->period_active = 1; + overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); + cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period); + cfs_b->expires_seq++; + hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); } static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) @@ -5654,8 +5257,6 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load, this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; } - - sched_avg_update(this_rq); } /* Used instead of source_load when we know the type == 0 */ @@ -6238,6 +5839,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p } #ifdef CONFIG_SCHED_SMT +DEFINE_STATIC_KEY_FALSE(sched_smt_present); static inline void set_idle_cores(int cpu, int val) { @@ -7295,8 +6897,8 @@ static int task_hot(struct task_struct *p, struct lb_env *env) static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { struct numa_group *numa_group = rcu_dereference(p->numa_group); - unsigned long src_faults, dst_faults; - int src_nid, dst_nid; + unsigned long src_weight, dst_weight; + int src_nid, dst_nid, dist; if (!static_branch_likely(&sched_numa_balancing)) return -1; @@ -7323,18 +6925,19 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) return 0; /* Leaving a core idle is often worse than degrading locality. */ - if (env->idle != CPU_NOT_IDLE) + if (env->idle == CPU_IDLE) return -1; + dist = node_distance(src_nid, dst_nid); if (numa_group) { - src_faults = group_faults(p, src_nid); - dst_faults = group_faults(p, dst_nid); + src_weight = group_weight(p, src_nid, dist); + dst_weight = group_weight(p, dst_nid, dist); } else { - src_faults = task_faults(p, src_nid); - dst_faults = task_faults(p, dst_nid); + src_weight = task_weight(p, src_nid, dist); + dst_weight = task_weight(p, dst_nid, dist); } - return dst_faults < src_faults; + return dst_weight < src_weight; } #else @@ -7621,6 +7224,22 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) return false; } +static inline bool others_have_blocked(struct rq *rq) +{ + if (READ_ONCE(rq->avg_rt.util_avg)) + return true; + + if (READ_ONCE(rq->avg_dl.util_avg)) + return true; + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + if (READ_ONCE(rq->avg_irq.util_avg)) + return true; +#endif + + return false; +} + #ifdef CONFIG_FAIR_GROUP_SCHED static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) @@ -7680,6 +7299,12 @@ static void update_blocked_averages(int cpu) if (cfs_rq_has_blocked(cfs_rq)) done = false; } + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + update_irq_load_avg(rq, 0); + /* Don't need periodic decay once load/util_avg are null */ + if (others_have_blocked(rq)) + done = false; #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; @@ -7745,9 +7370,12 @@ static inline void update_blocked_averages(int cpu) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + update_irq_load_avg(rq, 0); #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; - if (!cfs_rq_has_blocked(cfs_rq)) + if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq)) rq->has_blocked_load = 0; #endif rq_unlock_irqrestore(rq, &rf); @@ -7857,39 +7485,32 @@ static inline int get_sd_load_idx(struct sched_domain *sd, static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); - u64 total, used, age_stamp, avg; - s64 delta; + unsigned long max = arch_scale_cpu_capacity(NULL, cpu); + unsigned long used, free; + unsigned long irq; - /* - * Since we're reading these variables without serialization make sure - * we read them once before doing sanity checks on them. - */ - age_stamp = READ_ONCE(rq->age_stamp); - avg = READ_ONCE(rq->rt_avg); - delta = __rq_clock_broken(rq) - age_stamp; + irq = cpu_util_irq(rq); - if (unlikely(delta < 0)) - delta = 0; + if (unlikely(irq >= max)) + return 1; - total = sched_avg_period() + delta; + used = READ_ONCE(rq->avg_rt.util_avg); + used += READ_ONCE(rq->avg_dl.util_avg); - used = div_u64(avg, total); + if (unlikely(used >= max)) + return 1; - if (likely(used < SCHED_CAPACITY_SCALE)) - return SCHED_CAPACITY_SCALE - used; + free = max - used; - return 1; + return scale_irq_capacity(free, irq, max); } static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity = arch_scale_cpu_capacity(sd, cpu); + unsigned long capacity = scale_rt_capacity(cpu); struct sched_group *sdg = sd->groups; - cpu_rq(cpu)->cpu_capacity_orig = capacity; - - capacity *= scale_rt_capacity(cpu); - capacity >>= SCHED_CAPACITY_SHIFT; + cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu); if (!capacity) capacity = 1; @@ -10215,10 +9836,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) struct cfs_rq *cfs_rq; int i; - tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); + tg->cfs_rq = kcalloc(nr_cpu_ids, sizeof(cfs_rq), GFP_KERNEL); if (!tg->cfs_rq) goto err; - tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL); + tg->se = kcalloc(nr_cpu_ids, sizeof(se), GFP_KERNEL); if (!tg->se) goto err; diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c new file mode 100644 index 000000000000..35475c0c5419 --- /dev/null +++ b/kernel/sched/pelt.c @@ -0,0 +1,399 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Per Entity Load Tracking + * + * Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * Interactivity improvements by Mike Galbraith + * (C) 2007 Mike Galbraith <efault@gmx.de> + * + * Various enhancements by Dmitry Adamushko. + * (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com> + * + * Group scheduling enhancements by Srivatsa Vaddagiri + * Copyright IBM Corporation, 2007 + * Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> + * + * Scaled math optimizations by Thomas Gleixner + * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de> + * + * Adaptive scheduling granularity, math enhancements by Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * + * Move PELT related code from fair.c into this pelt.c file + * Author: Vincent Guittot <vincent.guittot@linaro.org> + */ + +#include <linux/sched.h> +#include "sched.h" +#include "sched-pelt.h" +#include "pelt.h" + +/* + * Approximate: + * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) + */ +static u64 decay_load(u64 val, u64 n) +{ + unsigned int local_n; + + if (unlikely(n > LOAD_AVG_PERIOD * 63)) + return 0; + + /* after bounds checking we can collapse to 32-bit */ + local_n = n; + + /* + * As y^PERIOD = 1/2, we can combine + * y^n = 1/2^(n/PERIOD) * y^(n%PERIOD) + * With a look-up table which covers y^n (n<PERIOD) + * + * To achieve constant time decay_load. + */ + if (unlikely(local_n >= LOAD_AVG_PERIOD)) { + val >>= local_n / LOAD_AVG_PERIOD; + local_n %= LOAD_AVG_PERIOD; + } + + val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32); + return val; +} + +static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) +{ + u32 c1, c2, c3 = d3; /* y^0 == 1 */ + + /* + * c1 = d1 y^p + */ + c1 = decay_load((u64)d1, periods); + + /* + * p-1 + * c2 = 1024 \Sum y^n + * n=1 + * + * inf inf + * = 1024 ( \Sum y^n - \Sum y^n - y^0 ) + * n=0 n=p + */ + c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024; + + return c1 + c2 + c3; +} + +#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT) + +/* + * Accumulate the three separate parts of the sum; d1 the remainder + * of the last (incomplete) period, d2 the span of full periods and d3 + * the remainder of the (incomplete) current period. + * + * d1 d2 d3 + * ^ ^ ^ + * | | | + * |<->|<----------------->|<--->| + * ... |---x---|------| ... |------|-----x (now) + * + * p-1 + * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0 + * n=1 + * + * = u y^p + (Step 1) + * + * p-1 + * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2) + * n=1 + */ +static __always_inline u32 +accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, + unsigned long load, unsigned long runnable, int running) +{ + unsigned long scale_freq, scale_cpu; + u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ + u64 periods; + + scale_freq = arch_scale_freq_capacity(cpu); + scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + + delta += sa->period_contrib; + periods = delta / 1024; /* A period is 1024us (~1ms) */ + + /* + * Step 1: decay old *_sum if we crossed period boundaries. + */ + if (periods) { + sa->load_sum = decay_load(sa->load_sum, periods); + sa->runnable_load_sum = + decay_load(sa->runnable_load_sum, periods); + sa->util_sum = decay_load((u64)(sa->util_sum), periods); + + /* + * Step 2 + */ + delta %= 1024; + contrib = __accumulate_pelt_segments(periods, + 1024 - sa->period_contrib, delta); + } + sa->period_contrib = delta; + + contrib = cap_scale(contrib, scale_freq); + if (load) + sa->load_sum += load * contrib; + if (runnable) + sa->runnable_load_sum += runnable * contrib; + if (running) + sa->util_sum += contrib * scale_cpu; + + return periods; +} + +/* + * We can represent the historical contribution to runnable average as the + * coefficients of a geometric series. To do this we sub-divide our runnable + * history into segments of approximately 1ms (1024us); label the segment that + * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g. + * + * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ... + * p0 p1 p2 + * (now) (~1ms ago) (~2ms ago) + * + * Let u_i denote the fraction of p_i that the entity was runnable. + * + * We then designate the fractions u_i as our co-efficients, yielding the + * following representation of historical load: + * u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ... + * + * We choose y based on the with of a reasonably scheduling period, fixing: + * y^32 = 0.5 + * + * This means that the contribution to load ~32ms ago (u_32) will be weighted + * approximately half as much as the contribution to load within the last ms + * (u_0). + * + * When a period "rolls over" and we have new u_0`, multiplying the previous + * sum again by y is sufficient to update: + * load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... ) + * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] + */ +static __always_inline int +___update_load_sum(u64 now, int cpu, struct sched_avg *sa, + unsigned long load, unsigned long runnable, int running) +{ + u64 delta; + + delta = now - sa->last_update_time; + /* + * This should only happen when time goes backwards, which it + * unfortunately does during sched clock init when we swap over to TSC. + */ + if ((s64)delta < 0) { + sa->last_update_time = now; + return 0; + } + + /* + * Use 1024ns as the unit of measurement since it's a reasonable + * approximation of 1us and fast to compute. + */ + delta >>= 10; + if (!delta) + return 0; + + sa->last_update_time += delta << 10; + + /* + * running is a subset of runnable (weight) so running can't be set if + * runnable is clear. But there are some corner cases where the current + * se has been already dequeued but cfs_rq->curr still points to it. + * This means that weight will be 0 but not running for a sched_entity + * but also for a cfs_rq if the latter becomes idle. As an example, + * this happens during idle_balance() which calls + * update_blocked_averages() + */ + if (!load) + runnable = running = 0; + + /* + * Now we know we crossed measurement unit boundaries. The *_avg + * accrues by two steps: + * + * Step 1: accumulate *_sum since last_update_time. If we haven't + * crossed period boundaries, finish. + */ + if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) + return 0; + + return 1; +} + +static __always_inline void +___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable) +{ + u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib; + + /* + * Step 2: update *_avg. + */ + sa->load_avg = div_u64(load * sa->load_sum, divider); + sa->runnable_load_avg = div_u64(runnable * sa->runnable_load_sum, divider); + WRITE_ONCE(sa->util_avg, sa->util_sum / divider); +} + +/* + * sched_entity: + * + * task: + * se_runnable() == se_weight() + * + * group: [ see update_cfs_group() ] + * se_weight() = tg->weight * grq->load_avg / tg->load_avg + * se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg + * + * load_sum := runnable_sum + * load_avg = se_weight(se) * runnable_avg + * + * runnable_load_sum := runnable_sum + * runnable_load_avg = se_runnable(se) * runnable_avg + * + * XXX collapse load_sum and runnable_load_sum + * + * cfq_rq: + * + * load_sum = \Sum se_weight(se) * se->avg.load_sum + * load_avg = \Sum se->avg.load_avg + * + * runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum + * runnable_load_avg = \Sum se->avg.runable_load_avg + */ + +int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) +{ + if (entity_is_task(se)) + se->runnable_weight = se->load.weight; + + if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { + ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); + return 1; + } + + return 0; +} + +int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + if (entity_is_task(se)) + se->runnable_weight = se->load.weight; + + if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, + cfs_rq->curr == se)) { + + ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); + cfs_se_util_change(&se->avg); + return 1; + } + + return 0; +} + +int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) +{ + if (___update_load_sum(now, cpu, &cfs_rq->avg, + scale_load_down(cfs_rq->load.weight), + scale_load_down(cfs_rq->runnable_weight), + cfs_rq->curr != NULL)) { + + ___update_load_avg(&cfs_rq->avg, 1, 1); + return 1; + } + + return 0; +} + +/* + * rt_rq: + * + * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked + * util_sum = cpu_scale * load_sum + * runnable_load_sum = load_sum + * + * load_avg and runnable_load_avg are not supported and meaningless. + * + */ + +int update_rt_rq_load_avg(u64 now, struct rq *rq, int running) +{ + if (___update_load_sum(now, rq->cpu, &rq->avg_rt, + running, + running, + running)) { + + ___update_load_avg(&rq->avg_rt, 1, 1); + return 1; + } + + return 0; +} + +/* + * dl_rq: + * + * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked + * util_sum = cpu_scale * load_sum + * runnable_load_sum = load_sum + * + */ + +int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) +{ + if (___update_load_sum(now, rq->cpu, &rq->avg_dl, + running, + running, + running)) { + + ___update_load_avg(&rq->avg_dl, 1, 1); + return 1; + } + + return 0; +} + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +/* + * irq: + * + * util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked + * util_sum = cpu_scale * load_sum + * runnable_load_sum = load_sum + * + */ + +int update_irq_load_avg(struct rq *rq, u64 running) +{ + int ret = 0; + /* + * We know the time that has been used by interrupt since last update + * but we don't when. Let be pessimistic and assume that interrupt has + * happened just before the update. This is not so far from reality + * because interrupt will most probably wake up task and trig an update + * of rq clock during which the metric si updated. + * We start to decay with normal context time and then we add the + * interrupt context time. + * We can safely remove running from rq->clock because + * rq->clock += delta with delta >= running + */ + ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq, + 0, + 0, + 0); + ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq, + 1, + 1, + 1); + + if (ret) + ___update_load_avg(&rq->avg_irq, 1, 1); + + return ret; +} +#endif diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h new file mode 100644 index 000000000000..d2894db28955 --- /dev/null +++ b/kernel/sched/pelt.h @@ -0,0 +1,72 @@ +#ifdef CONFIG_SMP + +int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se); +int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se); +int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq); +int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); +int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +int update_irq_load_avg(struct rq *rq, u64 running); +#else +static inline int +update_irq_load_avg(struct rq *rq, u64 running) +{ + return 0; +} +#endif + +/* + * When a task is dequeued, its estimated utilization should not be update if + * its util_avg has not been updated at least once. + * This flag is used to synchronize util_avg updates with util_est updates. + * We map this information into the LSB bit of the utilization saved at + * dequeue time (i.e. util_est.dequeued). + */ +#define UTIL_AVG_UNCHANGED 0x1 + +static inline void cfs_se_util_change(struct sched_avg *avg) +{ + unsigned int enqueued; + + if (!sched_feat(UTIL_EST)) + return; + + /* Avoid store if the flag has been already set */ + enqueued = avg->util_est.enqueued; + if (!(enqueued & UTIL_AVG_UNCHANGED)) + return; + + /* Reset flag to report util_avg has been updated */ + enqueued &= ~UTIL_AVG_UNCHANGED; + WRITE_ONCE(avg->util_est.enqueued, enqueued); +} + +#else + +static inline int +update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int +update_rt_rq_load_avg(u64 now, struct rq *rq, int running) +{ + return 0; +} + +static inline int +update_dl_rq_load_avg(u64 now, struct rq *rq, int running) +{ + return 0; +} + +static inline int +update_irq_load_avg(struct rq *rq, u64 running) +{ + return 0; +} +#endif + + diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index ef3c4e6f5345..2e2955a8cf8f 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -5,6 +5,8 @@ */ #include "sched.h" +#include "pelt.h" + int sched_rr_timeslice = RR_TIMESLICE; int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; @@ -183,10 +185,10 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) struct sched_rt_entity *rt_se; int i; - tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL); + tg->rt_rq = kcalloc(nr_cpu_ids, sizeof(rt_rq), GFP_KERNEL); if (!tg->rt_rq) goto err; - tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL); + tg->rt_se = kcalloc(nr_cpu_ids, sizeof(rt_se), GFP_KERNEL); if (!tg->rt_se) goto err; @@ -508,8 +510,11 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; - if (!rt_se) + if (!rt_se) { dequeue_top_rt_rq(rt_rq); + /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ + cpufreq_update_util(rq_of_rt_rq(rt_rq), 0); + } else if (on_rt_rq(rt_se)) dequeue_rt_entity(rt_se, 0); } @@ -833,6 +838,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) * can be time-consuming. Try to avoid it when possible. */ raw_spin_lock(&rt_rq->rt_runtime_lock); + if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF) + rt_rq->rt_runtime = rt_b->rt_runtime; skip = !rt_rq->rt_time && !rt_rq->rt_nr_running; raw_spin_unlock(&rt_rq->rt_runtime_lock); if (skip) @@ -968,8 +975,6 @@ static void update_curr_rt(struct rq *rq) curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); - sched_rt_avg_update(rq, delta_exec); - if (!rt_bandwidth_enabled()) return; @@ -1001,8 +1006,6 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq) sub_nr_running(rq, rt_rq->rt_nr_running); rt_rq->rt_queued = 0; - /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ - cpufreq_update_util(rq, 0); } static void @@ -1014,11 +1017,14 @@ enqueue_top_rt_rq(struct rt_rq *rt_rq) if (rt_rq->rt_queued) return; - if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running) + + if (rt_rq_throttled(rt_rq)) return; - add_nr_running(rq, rt_rq->rt_nr_running); - rt_rq->rt_queued = 1; + if (rt_rq->rt_nr_running) { + add_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 1; + } /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ cpufreq_update_util(rq, 0); @@ -1572,6 +1578,14 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) rt_queue_push_tasks(rq); + /* + * If prev task was rt, put_prev_task() has already updated the + * utilization. We only care of the case where we start to schedule a + * rt task + */ + if (rq->curr->sched_class != &rt_sched_class) + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + return p; } @@ -1579,6 +1593,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + /* * The previous task needs to be made eligible for pushing * if it is still active @@ -2308,6 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); watchdog(rq, p); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 6601baf2361c..4a2e8cae63c4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -334,9 +334,10 @@ struct cfs_bandwidth { u64 runtime; s64 hierarchical_quota; u64 runtime_expires; + int expires_seq; - int idle; - int period_active; + short idle; + short period_active; struct hrtimer period_timer; struct hrtimer slack_timer; struct list_head throttled_cfs_rq; @@ -551,6 +552,7 @@ struct cfs_rq { #ifdef CONFIG_CFS_BANDWIDTH int runtime_enabled; + int expires_seq; u64 runtime_expires; s64 runtime_remaining; @@ -592,6 +594,7 @@ struct rt_rq { unsigned long rt_nr_total; int overloaded; struct plist_head pushable_tasks; + #endif /* CONFIG_SMP */ int rt_queued; @@ -609,6 +612,11 @@ struct rt_rq { #endif }; +static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq) +{ + return rt_rq->rt_queued && rt_rq->rt_nr_running; +} + /* Deadline class' related fields in a runqueue */ struct dl_rq { /* runqueue is an rbtree, ordered by deadline */ @@ -666,7 +674,26 @@ struct dl_rq { u64 bw_ratio; }; +#ifdef CONFIG_FAIR_GROUP_SCHED +/* An entity is a task if it doesn't "own" a runqueue */ +#define entity_is_task(se) (!se->my_q) +#else +#define entity_is_task(se) 1 +#endif + #ifdef CONFIG_SMP +/* + * XXX we want to get rid of these helpers and use the full load resolution. + */ +static inline long se_weight(struct sched_entity *se) +{ + return scale_load_down(se->load.weight); +} + +static inline long se_runnable(struct sched_entity *se) +{ + return scale_load_down(se->runnable_weight); +} static inline bool sched_asym_prefer(int a, int b) { @@ -826,8 +853,12 @@ struct rq { struct list_head cfs_tasks; - u64 rt_avg; - u64 age_stamp; + struct sched_avg avg_rt; + struct sched_avg avg_dl; +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +#define HAVE_SCHED_AVG_IRQ + struct sched_avg avg_irq; +#endif u64 idle_stamp; u64 avg_idle; @@ -1068,7 +1099,8 @@ enum numa_faults_stats { }; extern void sched_setnuma(struct task_struct *p, int node); extern int migrate_task_to(struct task_struct *p, int cpu); -extern int migrate_swap(struct task_struct *, struct task_struct *); +extern int migrate_swap(struct task_struct *p, struct task_struct *t, + int cpu, int scpu); extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p); #else static inline void @@ -1683,15 +1715,9 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); -extern const_debug unsigned int sysctl_sched_time_avg; extern const_debug unsigned int sysctl_sched_nr_migrate; extern const_debug unsigned int sysctl_sched_migration_cost; -static inline u64 sched_avg_period(void) -{ - return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; -} - #ifdef CONFIG_SCHED_HRTICK /* @@ -1728,8 +1754,6 @@ unsigned long arch_scale_freq_capacity(int cpu) #endif #ifdef CONFIG_SMP -extern void sched_avg_update(struct rq *rq); - #ifndef arch_scale_cpu_capacity static __always_inline unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) @@ -1740,12 +1764,6 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) return SCHED_CAPACITY_SCALE; } #endif - -static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) -{ - rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq)); - sched_avg_update(rq); -} #else #ifndef arch_scale_cpu_capacity static __always_inline @@ -1754,8 +1772,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) return SCHED_CAPACITY_SCALE; } #endif -static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } -static inline void sched_avg_update(struct rq *rq) { } #endif struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) @@ -2170,11 +2186,16 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL -static inline unsigned long cpu_util_dl(struct rq *rq) +static inline unsigned long cpu_bw_dl(struct rq *rq) { return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT; } +static inline unsigned long cpu_util_dl(struct rq *rq) +{ + return READ_ONCE(rq->avg_dl.util_avg); +} + static inline unsigned long cpu_util_cfs(struct rq *rq) { unsigned long util = READ_ONCE(rq->cfs.avg.util_avg); @@ -2186,4 +2207,37 @@ static inline unsigned long cpu_util_cfs(struct rq *rq) return util; } + +static inline unsigned long cpu_util_rt(struct rq *rq) +{ + return READ_ONCE(rq->avg_rt.util_avg); +} +#endif + +#ifdef HAVE_SCHED_AVG_IRQ +static inline unsigned long cpu_util_irq(struct rq *rq) +{ + return rq->avg_irq.util_avg; +} + +static inline +unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max) +{ + util *= (max - irq); + util /= max; + + return util; + +} +#else +static inline unsigned long cpu_util_irq(struct rq *rq) +{ + return 0; +} + +static inline +unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max) +{ + return util; +} #endif diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index b6fb2c3b3ff7..66b59ac77c22 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -32,7 +32,7 @@ void swake_up_locked(struct swait_queue_head *q) } EXPORT_SYMBOL(swake_up_locked); -void swake_up(struct swait_queue_head *q) +void swake_up_one(struct swait_queue_head *q) { unsigned long flags; @@ -40,7 +40,7 @@ void swake_up(struct swait_queue_head *q) swake_up_locked(q); raw_spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL(swake_up); +EXPORT_SYMBOL(swake_up_one); /* * Does not allow usage from IRQ disabled, since we must be able to @@ -69,14 +69,14 @@ void swake_up_all(struct swait_queue_head *q) } EXPORT_SYMBOL(swake_up_all); -void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) +static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) { wait->task = current; if (list_empty(&wait->task_list)) - list_add(&wait->task_list, &q->task_list); + list_add_tail(&wait->task_list, &q->task_list); } -void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) +void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state) { unsigned long flags; @@ -85,16 +85,28 @@ void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int set_current_state(state); raw_spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL(prepare_to_swait); +EXPORT_SYMBOL(prepare_to_swait_exclusive); long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) { - if (signal_pending_state(state, current)) - return -ERESTARTSYS; + unsigned long flags; + long ret = 0; - prepare_to_swait(q, wait, state); + raw_spin_lock_irqsave(&q->lock, flags); + if (unlikely(signal_pending_state(state, current))) { + /* + * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one() + * must not see us. + */ + list_del_init(&wait->task_list); + ret = -ERESTARTSYS; + } else { + __prepare_to_swait(q, wait); + set_current_state(state); + } + raw_spin_unlock_irqrestore(&q->lock, flags); - return 0; + return ret; } EXPORT_SYMBOL(prepare_to_swait_event); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 61a1125c1ae4..56a0fed30c0a 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -47,7 +47,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu); } - if (!cpumask_test_cpu(cpu, sched_group_span(group))) { + if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) { printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu); } @@ -1750,7 +1750,7 @@ cpumask_var_t *alloc_sched_domains(unsigned int ndoms) int i; cpumask_var_t *doms; - doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); + doms = kmalloc_array(ndoms, sizeof(*doms), GFP_KERNEL); if (!doms) return NULL; for (i = 0; i < ndoms; i++) { diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 928be527477e..870f97b313e3 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -134,8 +134,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: is directly passed to the wakeup function * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) @@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark); * * On UP it can prevent extra preemption. * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. */ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive, void *key) @@ -392,35 +392,36 @@ static inline bool is_kthread_should_stop(void) * if (condition) * break; * - * p->state = mode; condition = true; - * smp_mb(); // A smp_wmb(); // C - * if (!wq_entry->flags & WQ_FLAG_WOKEN) wq_entry->flags |= WQ_FLAG_WOKEN; - * schedule() try_to_wake_up(); - * p->state = TASK_RUNNING; ~~~~~~~~~~~~~~~~~~ - * wq_entry->flags &= ~WQ_FLAG_WOKEN; condition = true; - * smp_mb() // B smp_wmb(); // C - * wq_entry->flags |= WQ_FLAG_WOKEN; - * } - * remove_wait_queue(&wq_head, &wait); + * // in wait_woken() // in woken_wake_function() * + * p->state = mode; wq_entry->flags |= WQ_FLAG_WOKEN; + * smp_mb(); // A try_to_wake_up(): + * if (!(wq_entry->flags & WQ_FLAG_WOKEN)) <full barrier> + * schedule() if (p->state & mode) + * p->state = TASK_RUNNING; p->state = TASK_RUNNING; + * wq_entry->flags &= ~WQ_FLAG_WOKEN; ~~~~~~~~~~~~~~~~~~ + * smp_mb(); // B condition = true; + * } smp_mb(); // C + * remove_wait_queue(&wq_head, &wait); wq_entry->flags |= WQ_FLAG_WOKEN; */ long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout) { - set_current_state(mode); /* A */ /* - * The above implies an smp_mb(), which matches with the smp_wmb() from - * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must - * also observe all state before the wakeup. + * The below executes an smp_mb(), which matches with the full barrier + * executed by the try_to_wake_up() in woken_wake_function() such that + * either we see the store to wq_entry->flags in woken_wake_function() + * or woken_wake_function() sees our store to current->state. */ + set_current_state(mode); /* A */ if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop()) timeout = schedule_timeout(timeout); __set_current_state(TASK_RUNNING); /* - * The below implies an smp_mb(), it too pairs with the smp_wmb() from - * woken_wake_function() such that we must either observe the wait - * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss - * an event. + * The below executes an smp_mb(), which matches with the smp_mb() (C) + * in woken_wake_function() such that either we see the wait condition + * being true or the store to wq_entry->flags in woken_wake_function() + * follows ours in the coherence order. */ smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */ @@ -430,14 +431,8 @@ EXPORT_SYMBOL(wait_woken); int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key) { - /* - * Although this function is called under waitqueue lock, LOCK - * doesn't imply write barrier and the users expects write - * barrier semantics on wakeup functions. The following - * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() - * and is paired with smp_store_mb() in wait_woken(). - */ - smp_wmb(); /* C */ + /* Pairs with the smp_store_mb() in wait_woken(). */ + smp_mb(); /* C */ wq_entry->flags |= WQ_FLAG_WOKEN; return default_wake_function(wq_entry, mode, sync, key); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index e691d9a6c58d..fd023ac24e10 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -593,18 +593,15 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, } /* - * Force an audit message to be emitted when the action is RET_KILL_*, - * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is - * allowed to be logged by the admin. + * Emit an audit message when the action is RET_KILL_*, RET_LOG, or the + * FILTER_FLAG_LOG bit was set. The admin has the ability to silence + * any action from being logged by removing the action name from the + * seccomp_actions_logged sysctl. */ - if (log) - return __audit_seccomp(syscall, signr, action); + if (!log) + return; - /* - * Let the audit subsystem decide if the action should be audited based - * on whether the current task itself is being audited. - */ - return audit_seccomp(syscall, signr, action); + audit_seccomp(syscall, signr, action); } /* @@ -1144,10 +1141,11 @@ static const struct seccomp_log_name seccomp_log_names[] = { }; static bool seccomp_names_from_actions_logged(char *names, size_t size, - u32 actions_logged) + u32 actions_logged, + const char *sep) { const struct seccomp_log_name *cur; - bool append_space = false; + bool append_sep = false; for (cur = seccomp_log_names; cur->name && size; cur++) { ssize_t ret; @@ -1155,15 +1153,15 @@ static bool seccomp_names_from_actions_logged(char *names, size_t size, if (!(actions_logged & cur->log)) continue; - if (append_space) { - ret = strscpy(names, " ", size); + if (append_sep) { + ret = strscpy(names, sep, size); if (ret < 0) return false; names += ret; size -= ret; } else - append_space = true; + append_sep = true; ret = strscpy(names, cur->name, size); if (ret < 0) @@ -1208,46 +1206,102 @@ static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names) return true; } -static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) +static int read_actions_logged(struct ctl_table *ro_table, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + char names[sizeof(seccomp_actions_avail)]; + struct ctl_table table; + + memset(names, 0, sizeof(names)); + + if (!seccomp_names_from_actions_logged(names, sizeof(names), + seccomp_actions_logged, " ")) + return -EINVAL; + + table = *ro_table; + table.data = names; + table.maxlen = sizeof(names); + return proc_dostring(&table, 0, buffer, lenp, ppos); +} + +static int write_actions_logged(struct ctl_table *ro_table, void __user *buffer, + size_t *lenp, loff_t *ppos, u32 *actions_logged) { char names[sizeof(seccomp_actions_avail)]; struct ctl_table table; int ret; - if (write && !capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) return -EPERM; memset(names, 0, sizeof(names)); - if (!write) { - if (!seccomp_names_from_actions_logged(names, sizeof(names), - seccomp_actions_logged)) - return -EINVAL; - } - table = *ro_table; table.data = names; table.maxlen = sizeof(names); - ret = proc_dostring(&table, write, buffer, lenp, ppos); + ret = proc_dostring(&table, 1, buffer, lenp, ppos); if (ret) return ret; - if (write) { - u32 actions_logged; + if (!seccomp_actions_logged_from_names(actions_logged, table.data)) + return -EINVAL; - if (!seccomp_actions_logged_from_names(&actions_logged, - table.data)) - return -EINVAL; + if (*actions_logged & SECCOMP_LOG_ALLOW) + return -EINVAL; - if (actions_logged & SECCOMP_LOG_ALLOW) - return -EINVAL; + seccomp_actions_logged = *actions_logged; + return 0; +} - seccomp_actions_logged = actions_logged; - } +static void audit_actions_logged(u32 actions_logged, u32 old_actions_logged, + int ret) +{ + char names[sizeof(seccomp_actions_avail)]; + char old_names[sizeof(seccomp_actions_avail)]; + const char *new = names; + const char *old = old_names; - return 0; + if (!audit_enabled) + return; + + memset(names, 0, sizeof(names)); + memset(old_names, 0, sizeof(old_names)); + + if (ret) + new = "?"; + else if (!actions_logged) + new = "(none)"; + else if (!seccomp_names_from_actions_logged(names, sizeof(names), + actions_logged, ",")) + new = "?"; + + if (!old_actions_logged) + old = "(none)"; + else if (!seccomp_names_from_actions_logged(old_names, + sizeof(old_names), + old_actions_logged, ",")) + old = "?"; + + return audit_seccomp_actions_logged(new, old, !ret); +} + +static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + if (write) { + u32 actions_logged = 0; + u32 old_actions_logged = seccomp_actions_logged; + + ret = write_actions_logged(ro_table, buffer, lenp, ppos, + &actions_logged); + audit_actions_logged(actions_logged, old_actions_logged, ret); + } else + ret = read_actions_logged(ro_table, buffer, lenp, ppos); + + return ret; } static struct ctl_path seccomp_sysctl_path[] = { diff --git a/kernel/signal.c b/kernel/signal.c index 0f865d67415d..8d8a940422a8 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1244,19 +1244,12 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, { struct sighand_struct *sighand; + rcu_read_lock(); for (;;) { - /* - * Disable interrupts early to avoid deadlocks. - * See rcu_read_unlock() comment header for details. - */ - local_irq_save(*flags); - rcu_read_lock(); sighand = rcu_dereference(tsk->sighand); - if (unlikely(sighand == NULL)) { - rcu_read_unlock(); - local_irq_restore(*flags); + if (unlikely(sighand == NULL)) break; - } + /* * This sighand can be already freed and even reused, but * we rely on SLAB_TYPESAFE_BY_RCU and sighand_ctor() which @@ -1268,15 +1261,12 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, * __exit_signal(). In the latter case the next iteration * must see ->sighand == NULL. */ - spin_lock(&sighand->siglock); - if (likely(sighand == tsk->sighand)) { - rcu_read_unlock(); + spin_lock_irqsave(&sighand->siglock, *flags); + if (likely(sighand == tsk->sighand)) break; - } - spin_unlock(&sighand->siglock); - rcu_read_unlock(); - local_irq_restore(*flags); + spin_unlock_irqrestore(&sighand->siglock, *flags); } + rcu_read_unlock(); return sighand; } diff --git a/kernel/smp.c b/kernel/smp.c index 084c8b3a2681..d86eec5f51c1 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -584,6 +584,8 @@ void __init smp_init(void) num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); + /* Final decision about SMT support */ + cpu_smt_check_topology(); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 5043e7433f4b..c230c2dd48e1 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -238,8 +238,7 @@ int smpboot_unpark_threads(unsigned int cpu) mutex_lock(&smpboot_threads_lock); list_for_each_entry(cur, &hotplug_threads, list) - if (cpumask_test_cpu(cpu, cur->cpumask)) - smpboot_unpark_thread(cur, cpu); + smpboot_unpark_thread(cur, cpu); mutex_unlock(&smpboot_threads_lock); return 0; } @@ -280,34 +279,26 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) } /** - * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related + * smpboot_register_percpu_thread - Register a per_cpu thread related * to hotplug * @plug_thread: Hotplug thread descriptor - * @cpumask: The cpumask where threads run * * Creates and starts the threads on all online cpus. */ -int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread, - const struct cpumask *cpumask) +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) { unsigned int cpu; int ret = 0; - if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL)) - return -ENOMEM; - cpumask_copy(plug_thread->cpumask, cpumask); - get_online_cpus(); mutex_lock(&smpboot_threads_lock); for_each_online_cpu(cpu) { ret = __smpboot_create_thread(plug_thread, cpu); if (ret) { smpboot_destroy_threads(plug_thread); - free_cpumask_var(plug_thread->cpumask); goto out; } - if (cpumask_test_cpu(cpu, cpumask)) - smpboot_unpark_thread(plug_thread, cpu); + smpboot_unpark_thread(plug_thread, cpu); } list_add(&plug_thread->list, &hotplug_threads); out: @@ -315,7 +306,7 @@ out: put_online_cpus(); return ret; } -EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask); +EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); /** * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug @@ -331,44 +322,9 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) smpboot_destroy_threads(plug_thread); mutex_unlock(&smpboot_threads_lock); put_online_cpus(); - free_cpumask_var(plug_thread->cpumask); } EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); -/** - * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked - * @plug_thread: Hotplug thread descriptor - * @new: Revised mask to use - * - * The cpumask field in the smp_hotplug_thread must not be updated directly - * by the client, but only by calling this function. - * This function can only be called on a registered smp_hotplug_thread. - */ -void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) -{ - struct cpumask *old = plug_thread->cpumask; - static struct cpumask tmp; - unsigned int cpu; - - lockdep_assert_cpus_held(); - mutex_lock(&smpboot_threads_lock); - - /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(&tmp, old, new); - for_each_cpu_and(cpu, &tmp, cpu_online_mask) - smpboot_park_thread(plug_thread, cpu); - - /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(&tmp, new, old); - for_each_cpu_and(cpu, &tmp, cpu_online_mask) - smpboot_unpark_thread(plug_thread, cpu); - - cpumask_copy(old, new); - - mutex_unlock(&smpboot_threads_lock); -} - static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); /* diff --git a/kernel/softirq.c b/kernel/softirq.c index de2f57fddc04..6f584861d329 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -79,12 +79,16 @@ static void wakeup_softirqd(void) /* * If ksoftirqd is scheduled, we do not want to process pending softirqs - * right now. Let ksoftirqd handle this at its own rate, to get fairness. + * right now. Let ksoftirqd handle this at its own rate, to get fairness, + * unless we're doing some of the synchronous softirqs. */ -static bool ksoftirqd_running(void) +#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ)) +static bool ksoftirqd_running(unsigned long pending) { struct task_struct *tsk = __this_cpu_read(ksoftirqd); + if (pending & SOFTIRQ_NOW_MASK) + return false; return tsk && (tsk->state == TASK_RUNNING); } @@ -139,9 +143,13 @@ static void __local_bh_enable(unsigned int cnt) { lockdep_assert_irqs_disabled(); + if (preempt_count() == cnt) + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); + if (softirq_count() == (cnt & SOFTIRQ_MASK)) trace_softirqs_on(_RET_IP_); - preempt_count_sub(cnt); + + __preempt_count_sub(cnt); } /* @@ -324,7 +332,7 @@ asmlinkage __visible void do_softirq(void) pending = local_softirq_pending(); - if (pending && !ksoftirqd_running()) + if (pending && !ksoftirqd_running(pending)) do_softirq_own_stack(); local_irq_restore(flags); @@ -351,7 +359,7 @@ void irq_enter(void) static inline void invoke_softirq(void) { - if (ksoftirqd_running()) + if (ksoftirqd_running(local_softirq_pending())) return; if (!force_irqthreads) { @@ -382,7 +390,7 @@ static inline void tick_irq_exit(void) /* Make sure that timer wheel updates are propagated */ if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) { - if (!in_interrupt()) + if (!in_irq()) tick_nohz_irq_exit(); } #endif diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index f89014a2c238..067cb83f37ea 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -81,6 +81,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) unsigned long flags; bool enabled; + preempt_disable(); raw_spin_lock_irqsave(&stopper->lock, flags); enabled = stopper->enabled; if (enabled) @@ -90,6 +91,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) raw_spin_unlock_irqrestore(&stopper->lock, flags); wake_up_q(&wakeq); + preempt_enable(); return enabled; } @@ -236,13 +238,24 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1, struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2); DEFINE_WAKE_Q(wakeq); int err; + retry: + /* + * The waking up of stopper threads has to happen in the same + * scheduling context as the queueing. Otherwise, there is a + * possibility of one of the above stoppers being woken up by another + * CPU, and preempting us. This will cause us to not wake up the other + * stopper forever. + */ + preempt_disable(); raw_spin_lock_irq(&stopper1->lock); raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); - err = -ENOENT; - if (!stopper1->enabled || !stopper2->enabled) + if (!stopper1->enabled || !stopper2->enabled) { + err = -ENOENT; goto unlock; + } + /* * Ensure that if we race with __stop_cpus() the stoppers won't get * queued up in reverse order leading to system deadlock. @@ -253,24 +266,30 @@ retry: * It can be falsely true but it is safe to spin until it is cleared, * queue_stop_cpus_work() does everything under preempt_disable(). */ - err = -EDEADLK; - if (unlikely(stop_cpus_in_progress)) - goto unlock; + if (unlikely(stop_cpus_in_progress)) { + err = -EDEADLK; + goto unlock; + } err = 0; __cpu_stop_queue_work(stopper1, work1, &wakeq); __cpu_stop_queue_work(stopper2, work2, &wakeq); + unlock: raw_spin_unlock(&stopper2->lock); raw_spin_unlock_irq(&stopper1->lock); if (unlikely(err == -EDEADLK)) { + preempt_enable(); + while (stop_cpus_in_progress) cpu_relax(); + goto retry; } wake_up_q(&wakeq); + preempt_enable(); return err; } diff --git a/kernel/sys.c b/kernel/sys.c index d1b2b8d934bb..e27b51d3facd 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2018,7 +2018,11 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data return error; } - down_write(&mm->mmap_sem); + /* + * arg_lock protects concurent updates but we still need mmap_sem for + * read to exclude races with sys_brk. + */ + down_read(&mm->mmap_sem); /* * We don't validate if these members are pointing to @@ -2032,6 +2036,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data * to any problem in kernel itself */ + spin_lock(&mm->arg_lock); mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; @@ -2043,6 +2048,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; + spin_unlock(&mm->arg_lock); /* * Note this update of @saved_auxv is lockless thus @@ -2055,7 +2061,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); - up_write(&mm->mmap_sem); + up_read(&mm->mmap_sem); return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ @@ -2506,11 +2512,11 @@ static int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; - struct timespec tp; + struct timespec64 tp; memset(info, 0, sizeof(struct sysinfo)); - get_monotonic_boottime(&tp); + ktime_get_boottime_ts64(&tp); info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 183169c2a75b..df556175be50 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -367,7 +367,7 @@ COND_SYSCALL(s390_pci_mmio_write); COND_SYSCALL_COMPAT(s390_ipc); /* powerpc */ -cond_syscall(ppc_rtas); +COND_SYSCALL(rtas); COND_SYSCALL(spu_run); COND_SYSCALL(spu_create); COND_SYSCALL(subpage_prot); @@ -432,3 +432,6 @@ COND_SYSCALL(setresgid16); COND_SYSCALL(setresuid16); COND_SYSCALL(setreuid16); COND_SYSCALL(setuid16); + +/* restartable sequence */ +COND_SYSCALL(rseq); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6a78cf70761d..f22f76b7a138 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -368,14 +368,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "sched_time_avg_ms", - .data = &sysctl_sched_time_avg, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - }, #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", @@ -3047,7 +3039,8 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, if (IS_ERR(kbuf)) return PTR_ERR(kbuf); - tmp_bitmap = kzalloc(BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long), + tmp_bitmap = kcalloc(BITS_TO_LONGS(bitmap_len), + sizeof(unsigned long), GFP_KERNEL); if (!tmp_bitmap) { kfree(kbuf); diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c index dd53e354f630..7bca480151b0 100644 --- a/kernel/test_kprobes.c +++ b/kernel/test_kprobes.c @@ -162,90 +162,6 @@ static int test_kprobes(void) } -#if 0 -static u32 jph_val; - -static u32 j_kprobe_target(u32 value) -{ - if (preemptible()) { - handler_errors++; - pr_err("jprobe-handler is preemptible\n"); - } - if (value != rand1) { - handler_errors++; - pr_err("incorrect value in jprobe handler\n"); - } - - jph_val = rand1; - jprobe_return(); - return 0; -} - -static struct jprobe jp = { - .entry = j_kprobe_target, - .kp.symbol_name = "kprobe_target" -}; - -static int test_jprobe(void) -{ - int ret; - - ret = register_jprobe(&jp); - if (ret < 0) { - pr_err("register_jprobe returned %d\n", ret); - return ret; - } - - ret = target(rand1); - unregister_jprobe(&jp); - if (jph_val == 0) { - pr_err("jprobe handler not called\n"); - handler_errors++; - } - - return 0; -} - -static struct jprobe jp2 = { - .entry = j_kprobe_target, - .kp.symbol_name = "kprobe_target2" -}; - -static int test_jprobes(void) -{ - int ret; - struct jprobe *jps[2] = {&jp, &jp2}; - - /* addr and flags should be cleard for reusing kprobe. */ - jp.kp.addr = NULL; - jp.kp.flags = 0; - ret = register_jprobes(jps, 2); - if (ret < 0) { - pr_err("register_jprobes returned %d\n", ret); - return ret; - } - - jph_val = 0; - ret = target(rand1); - if (jph_val == 0) { - pr_err("jprobe handler not called\n"); - handler_errors++; - } - - jph_val = 0; - ret = target2(rand1); - if (jph_val == 0) { - pr_err("jprobe handler2 not called\n"); - handler_errors++; - } - unregister_jprobes(jps, 2); - - return 0; -} -#else -#define test_jprobe() (0) -#define test_jprobes() (0) -#endif #ifdef CONFIG_KRETPROBES static u32 krph_val; @@ -383,16 +299,6 @@ int init_test_probes(void) if (ret < 0) errors++; - num_tests++; - ret = test_jprobe(); - if (ret < 0) - errors++; - - num_tests++; - ret = test_jprobes(); - if (ret < 0) - errors++; - #ifdef CONFIG_KRETPROBES num_tests++; ret = test_kretprobe(); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 639321bf2e39..fa5de5e8de61 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -581,11 +581,11 @@ static void alarm_timer_rearm(struct k_itimer *timr) * @timr: Pointer to the posixtimer data struct * @now: Current time to forward the timer against */ -static int alarm_timer_forward(struct k_itimer *timr, ktime_t now) +static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; - return (int) alarm_forward(alarm, timr->it_interval, now); + return alarm_forward(alarm, timr->it_interval, now); } /** @@ -808,7 +808,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, /* Convert (if necessary) to absolute time */ if (flags != TIMER_ABSTIME) { ktime_t now = alarm_bases[type].gettime(); - exp = ktime_add(now, exp); + + exp = ktime_add_safe(now, exp); } ret = alarmtimer_do_nsleep(&alarm, exp, type); diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 16c027e9cc73..8c0e4092f661 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -463,6 +463,12 @@ void clockevents_register_device(struct clock_event_device *dev) dev->cpumask = cpumask_of(smp_processor_id()); } + if (dev->cpumask == cpu_all_mask) { + WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n", + dev->name); + dev->cpumask = cpu_possible_mask; + } + raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index f89a78e2792b..f74fb00d8064 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -94,6 +94,8 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift); /*[Clocksource internal variables]--------- * curr_clocksource: * currently selected clocksource. + * suspend_clocksource: + * used to calculate the suspend time. * clocksource_list: * linked list with the registered clocksources * clocksource_mutex: @@ -102,10 +104,12 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift); * Name of the user-specified clocksource. */ static struct clocksource *curr_clocksource; +static struct clocksource *suspend_clocksource; static LIST_HEAD(clocksource_list); static DEFINE_MUTEX(clocksource_mutex); static char override_name[CS_NAME_LEN]; static int finished_booting; +static u64 suspend_start; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); @@ -447,6 +451,140 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) { } #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ +static bool clocksource_is_suspend(struct clocksource *cs) +{ + return cs == suspend_clocksource; +} + +static void __clocksource_suspend_select(struct clocksource *cs) +{ + /* + * Skip the clocksource which will be stopped in suspend state. + */ + if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP)) + return; + + /* + * The nonstop clocksource can be selected as the suspend clocksource to + * calculate the suspend time, so it should not supply suspend/resume + * interfaces to suspend the nonstop clocksource when system suspends. + */ + if (cs->suspend || cs->resume) { + pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n", + cs->name); + } + + /* Pick the best rating. */ + if (!suspend_clocksource || cs->rating > suspend_clocksource->rating) + suspend_clocksource = cs; +} + +/** + * clocksource_suspend_select - Select the best clocksource for suspend timing + * @fallback: if select a fallback clocksource + */ +static void clocksource_suspend_select(bool fallback) +{ + struct clocksource *cs, *old_suspend; + + old_suspend = suspend_clocksource; + if (fallback) + suspend_clocksource = NULL; + + list_for_each_entry(cs, &clocksource_list, list) { + /* Skip current if we were requested for a fallback. */ + if (fallback && cs == old_suspend) + continue; + + __clocksource_suspend_select(cs); + } +} + +/** + * clocksource_start_suspend_timing - Start measuring the suspend timing + * @cs: current clocksource from timekeeping + * @start_cycles: current cycles from timekeeping + * + * This function will save the start cycle values of suspend timer to calculate + * the suspend time when resuming system. + * + * This function is called late in the suspend process from timekeeping_suspend(), + * that means processes are freezed, non-boot cpus and interrupts are disabled + * now. It is therefore possible to start the suspend timer without taking the + * clocksource mutex. + */ +void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles) +{ + if (!suspend_clocksource) + return; + + /* + * If current clocksource is the suspend timer, we should use the + * tkr_mono.cycle_last value as suspend_start to avoid same reading + * from suspend timer. + */ + if (clocksource_is_suspend(cs)) { + suspend_start = start_cycles; + return; + } + + if (suspend_clocksource->enable && + suspend_clocksource->enable(suspend_clocksource)) { + pr_warn_once("Failed to enable the non-suspend-able clocksource.\n"); + return; + } + + suspend_start = suspend_clocksource->read(suspend_clocksource); +} + +/** + * clocksource_stop_suspend_timing - Stop measuring the suspend timing + * @cs: current clocksource from timekeeping + * @cycle_now: current cycles from timekeeping + * + * This function will calculate the suspend time from suspend timer. + * + * Returns nanoseconds since suspend started, 0 if no usable suspend clocksource. + * + * This function is called early in the resume process from timekeeping_resume(), + * that means there is only one cpu, no processes are running and the interrupts + * are disabled. It is therefore possible to stop the suspend timer without + * taking the clocksource mutex. + */ +u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) +{ + u64 now, delta, nsec = 0; + + if (!suspend_clocksource) + return 0; + + /* + * If current clocksource is the suspend timer, we should use the + * tkr_mono.cycle_last value from timekeeping as current cycle to + * avoid same reading from suspend timer. + */ + if (clocksource_is_suspend(cs)) + now = cycle_now; + else + now = suspend_clocksource->read(suspend_clocksource); + + if (now > suspend_start) { + delta = clocksource_delta(now, suspend_start, + suspend_clocksource->mask); + nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult, + suspend_clocksource->shift); + } + + /* + * Disable the suspend timer to save power if current clocksource is + * not the suspend timer. + */ + if (!clocksource_is_suspend(cs) && suspend_clocksource->disable) + suspend_clocksource->disable(suspend_clocksource); + + return nsec; +} + /** * clocksource_suspend - suspend the clocksource(s) */ @@ -792,6 +930,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) clocksource_select(); clocksource_select_watchdog(false); + __clocksource_suspend_select(cs); mutex_unlock(&clocksource_mutex); return 0; } @@ -820,6 +959,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating) clocksource_select(); clocksource_select_watchdog(false); + clocksource_suspend_select(false); mutex_unlock(&clocksource_mutex); } EXPORT_SYMBOL(clocksource_change_rating); @@ -845,6 +985,15 @@ static int clocksource_unbind(struct clocksource *cs) return -EBUSY; } + if (clocksource_is_suspend(cs)) { + /* + * Select and try to install a replacement suspend clocksource. + * If no replacement suspend clocksource, we will just let the + * clocksource go and have no suspend clocksource. + */ + clocksource_suspend_select(true); + } + clocksource_watchdog_lock(&flags); clocksource_dequeue_watchdog(cs); list_del_init(&cs->list); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 055a4a728c00..e1a549c9e399 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -718,8 +718,8 @@ static void hrtimer_switch_to_hres(void) struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { - printk(KERN_WARNING "Could not switch to high resolution " - "mode on CPU %d\n", base->cpu); + pr_warn("Could not switch to high resolution mode on CPU %u\n", + base->cpu); return; } base->hres_active = 1; @@ -1573,8 +1573,7 @@ retry: else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); - printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", - ktime_to_ns(delta)); + pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } /* called with interrupts disabled */ @@ -1659,7 +1658,7 @@ EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (compat_put_timespec64(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index a09ded765f6c..c5e0cba3b39c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -502,7 +502,7 @@ static void sched_sync_hw_clock(struct timespec64 now, { struct timespec64 next; - getnstimeofday64(&next); + ktime_get_real_ts64(&next); if (!fail) next.tv_sec = 659; else { @@ -537,7 +537,7 @@ static void sync_rtc_clock(void) if (!IS_ENABLED(CONFIG_RTC_SYSTOHC)) return; - getnstimeofday64(&now); + ktime_get_real_ts64(&now); adjust = now; if (persistent_clock_is_local) @@ -591,7 +591,7 @@ static bool sync_cmos_clock(void) * Architectures are strongly encouraged to use rtclib and not * implement this legacy API. */ - getnstimeofday64(&now); + ktime_get_real_ts64(&now); if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) { if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); @@ -642,7 +642,7 @@ void ntp_notify_cmos_timer(void) /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) +static inline void process_adj_status(const struct timex *txc) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; @@ -665,12 +665,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) } -static inline void process_adjtimex_modes(struct timex *txc, - struct timespec64 *ts, - s32 *time_tai) +static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai) { if (txc->modes & ADJ_STATUS) - process_adj_status(txc, ts); + process_adj_status(txc); if (txc->modes & ADJ_NANO) time_status |= STA_NANO; @@ -718,7 +716,7 @@ static inline void process_adjtimex_modes(struct timex *txc, * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ -int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) +int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) { int result; @@ -735,7 +733,7 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) /* If there are input parameters, then process them: */ if (txc->modes) - process_adjtimex_modes(txc, ts, time_tai); + process_adjtimex_modes(txc, time_tai); txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, NTP_SCALE_SHIFT); @@ -1022,12 +1020,11 @@ void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_t static int __init ntp_tick_adj_setup(char *str) { - int rc = kstrtol(str, 0, (long *)&ntp_tick_adj); - + int rc = kstrtos64(str, 0, &ntp_tick_adj); if (rc) return rc; - ntp_tick_adj <<= NTP_SCALE_SHIFT; + ntp_tick_adj <<= NTP_SCALE_SHIFT; return 1; } diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 909bd1f1bfb1..c24b0e13f011 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -8,6 +8,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern ktime_t ntp_get_next_leap(void); extern int second_overflow(time64_t secs); -extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); -extern void __hardpps(const struct timespec64 *, const struct timespec64 *); +extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai); +extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 5a6251ac6f7a..294d7b65af33 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -85,7 +85,7 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now) continue; timer->it.cpu.expires += incr; - timer->it_overrun += 1 << i; + timer->it_overrun += 1LL << i; delta -= incr; } } @@ -604,7 +604,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, /* * Disarm any old timer after extracting its expiry time. */ - lockdep_assert_irqs_disabled(); ret = 0; old_incr = timer->it.cpu.incr; @@ -1049,7 +1048,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) /* * Now re-arm for the new expiry time. */ - lockdep_assert_irqs_disabled(); arm_timer(timer); unlock: unlock_task_sighand(p, &flags); diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 26aa9569e24a..2c6847d5d69b 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -81,7 +81,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) ktime_get_ts64(tp); break; case CLOCK_BOOTTIME: - get_monotonic_boottime64(tp); + ktime_get_boottime_ts64(tp); break; default: return -EINVAL; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index e08ce3f27447..f23cc46ecf3e 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -86,15 +86,6 @@ static const struct k_clock clock_realtime, clock_monotonic; #endif /* - * parisc wants ENOTSUP instead of EOPNOTSUPP - */ -#ifndef ENOTSUP -# define ENANOSLEEP_NOTSUP EOPNOTSUPP -#else -# define ENANOSLEEP_NOTSUP ENOTSUP -#endif - -/* * The timer ID is turned into a timer address by idr_find(). * Verifying a valid ID consists of: * @@ -228,21 +219,21 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp) */ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp) { - getrawmonotonic64(tp); + ktime_get_raw_ts64(tp); return 0; } static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp) { - *tp = current_kernel_time64(); + ktime_get_coarse_real_ts64(tp); return 0; } static int posix_get_monotonic_coarse(clockid_t which_clock, struct timespec64 *tp) { - *tp = get_monotonic_coarse64(); + ktime_get_coarse_ts64(tp); return 0; } @@ -254,13 +245,13 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 * static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp) { - get_monotonic_boottime64(tp); + ktime_get_boottime_ts64(tp); return 0; } static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) { - timekeeping_clocktai64(tp); + ktime_get_clocktai_ts64(tp); return 0; } @@ -283,6 +274,17 @@ static __init int init_posix_timers(void) } __initcall(init_posix_timers); +/* + * The siginfo si_overrun field and the return value of timer_getoverrun(2) + * are of type int. Clamp the overrun value to INT_MAX + */ +static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval) +{ + s64 sum = timr->it_overrun_last + (s64)baseval; + + return sum > (s64)INT_MAX ? INT_MAX : (int)sum; +} + static void common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; @@ -290,9 +292,8 @@ static void common_hrtimer_rearm(struct k_itimer *timr) if (!timr->it_interval) return; - timr->it_overrun += (unsigned int) hrtimer_forward(timer, - timer->base->get_time(), - timr->it_interval); + timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(), + timr->it_interval); hrtimer_restart(timer); } @@ -321,10 +322,10 @@ void posixtimer_rearm(struct siginfo *info) timr->it_active = 1; timr->it_overrun_last = timr->it_overrun; - timr->it_overrun = -1; + timr->it_overrun = -1LL; ++timr->it_requeue_pending; - info->si_overrun += timr->it_overrun_last; + info->si_overrun = timer_overrun_to_int(timr, info->si_overrun); } unlock_timer(timr, flags); @@ -418,9 +419,8 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) now = ktime_add(now, kj); } #endif - timr->it_overrun += (unsigned int) - hrtimer_forward(timer, now, - timr->it_interval); + timr->it_overrun += hrtimer_forward(timer, now, + timr->it_interval); ret = HRTIMER_RESTART; ++timr->it_requeue_pending; timr->it_active = 1; @@ -524,7 +524,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, new_timer->it_id = (timer_t) new_timer_id; new_timer->it_clock = which_clock; new_timer->kclock = kc; - new_timer->it_overrun = -1; + new_timer->it_overrun = -1LL; if (event) { rcu_read_lock(); @@ -645,11 +645,11 @@ static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now) return __hrtimer_expires_remaining_adjusted(timer, now); } -static int common_hrtimer_forward(struct k_itimer *timr, ktime_t now) +static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now) { struct hrtimer *timer = &timr->it.real.timer; - return (int)hrtimer_forward(timer, now, timr->it_interval); + return hrtimer_forward(timer, now, timr->it_interval); } /* @@ -743,7 +743,7 @@ static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting) /* Get the time remaining on a POSIX.1b interval timer. */ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct itimerspec __user *, setting) + struct __kernel_itimerspec __user *, setting) { struct itimerspec64 cur_setting; @@ -755,7 +755,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, return ret; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME + COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, struct compat_itimerspec __user *, setting) { @@ -768,6 +769,7 @@ COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, } return ret; } + #endif /* @@ -789,7 +791,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) if (!timr) return -EINVAL; - overrun = timr->it_overrun_last; + overrun = timer_overrun_to_int(timr, 0); unlock_timer(timr, flags); return overrun; @@ -906,8 +908,8 @@ retry: /* Set a POSIX.1b interval timer */ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - const struct itimerspec __user *, new_setting, - struct itimerspec __user *, old_setting) + const struct __kernel_itimerspec __user *, new_setting, + struct __kernel_itimerspec __user *, old_setting) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old_setting ? &old_spec : NULL; @@ -927,7 +929,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, return error; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, struct compat_itimerspec __user *, new, struct compat_itimerspec __user *, old) @@ -1220,7 +1222,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, if (!kc) return -EINVAL; if (!kc->nsleep) - return -ENANOSLEEP_NOTSUP; + return -EOPNOTSUPP; if (get_timespec64(&t, rqtp)) return -EFAULT; @@ -1247,7 +1249,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, if (!kc) return -EINVAL; if (!kc->nsleep) - return -ENANOSLEEP_NOTSUP; + return -EOPNOTSUPP; if (compat_get_timespec64(&t, rqtp)) return -EFAULT; diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 151e28f5bf30..ddb21145211a 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -19,7 +19,7 @@ struct k_clock { void (*timer_get)(struct k_itimer *timr, struct itimerspec64 *cur_setting); void (*timer_rearm)(struct k_itimer *timr); - int (*timer_forward)(struct k_itimer *timr, ktime_t now); + s64 (*timer_forward)(struct k_itimer *timr, ktime_t now); ktime_t (*timer_remaining)(struct k_itimer *timr, ktime_t now); int (*timer_try_to_cancel)(struct k_itimer *timr); void (*timer_arm)(struct k_itimer *timr, ktime_t expires, diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 2d8f05aad442..cbc72c2c1fca 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -237,7 +237,7 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) pr_debug("Registered %pF as sched_clock source\n", read); } -void __init sched_clock_postinit(void) +void __init generic_sched_clock_init(void) { /* * If no sched_clock() function has been provided at that point, diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index 58045eb976c3..a59641fb88b6 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -90,7 +90,7 @@ static struct clock_event_device ce_broadcast_hrtimer = { .max_delta_ticks = ULONG_MAX, .mult = 1, .shift = 0, - .cpumask = cpu_all_mask, + .cpumask = cpu_possible_mask, }; static enum hrtimer_restart bc_handler(struct hrtimer *t) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index b7005dd21ec1..14de3727b18e 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -277,8 +277,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev, */ return !curdev || newdev->rating > curdev->rating || - (!cpumask_equal(curdev->cpumask, newdev->cpumask) && - !tick_check_percpu(curdev, newdev, smp_processor_id())); + !cpumask_equal(curdev->cpumask, newdev->cpumask); } /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index da9455a6b42b..5b33e2f5c0ed 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -642,7 +642,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) static inline bool local_timer_softirq_pending(void) { - return local_softirq_pending() & TIMER_SOFTIRQ; + return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) diff --git a/kernel/time/time.c b/kernel/time/time.c index 6fa99213fc72..ccdb351277ee 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -28,6 +28,7 @@ */ #include <linux/export.h> +#include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> @@ -63,7 +64,7 @@ EXPORT_SYMBOL(sys_tz); */ SYSCALL_DEFINE1(time, time_t __user *, tloc) { - time_t i = get_seconds(); + time_t i = (time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) @@ -106,11 +107,9 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr) /* compat_time_t is a 32 bit "long" and needs to get converted. */ COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) { - struct timeval tv; compat_time_t i; - do_gettimeofday(&tv); - i = tv.tv_sec; + i = (compat_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) @@ -314,9 +313,10 @@ unsigned int jiffies_to_msecs(const unsigned long j) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 - return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32; + return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> + HZ_TO_MSEC_SHR32; # else - return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN; + return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } @@ -929,7 +929,7 @@ int compat_put_timespec64(const struct timespec64 *ts, void __user *uts) EXPORT_SYMBOL_GPL(compat_put_timespec64); int get_itimerspec64(struct itimerspec64 *it, - const struct itimerspec __user *uit) + const struct __kernel_itimerspec __user *uit) { int ret; @@ -944,7 +944,7 @@ int get_itimerspec64(struct itimerspec64 *it, EXPORT_SYMBOL_GPL(get_itimerspec64); int put_itimerspec64(const struct itimerspec64 *it, - struct itimerspec __user *uit) + struct __kernel_itimerspec __user *uit) { int ret; @@ -957,3 +957,24 @@ int put_itimerspec64(const struct itimerspec64 *it, return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); + +int get_compat_itimerspec64(struct itimerspec64 *its, + const struct compat_itimerspec __user *uits) +{ + + if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || + __compat_get_timespec64(&its->it_value, &uits->it_value)) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(get_compat_itimerspec64); + +int put_compat_itimerspec64(const struct itimerspec64 *its, + struct compat_itimerspec __user *uits) +{ + if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || + __compat_put_timespec64(&its->it_value, &uits->it_value)) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(put_compat_itimerspec64); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 4786df904c22..f3b22f456fac 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -17,6 +17,7 @@ #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> +#include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> @@ -34,6 +35,14 @@ #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) +enum timekeeping_adv_mode { + /* Update timekeeper when a tick has passed */ + TK_ADV_TICK, + + /* Update timekeeper on a direct frequency change */ + TK_ADV_FREQ +}; + /* * The most important data for readout fits into a single 64 byte * cache line. @@ -97,7 +106,7 @@ static inline void tk_normalize_xtime(struct timekeeper *tk) } } -static inline struct timespec64 tk_xtime(struct timekeeper *tk) +static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; @@ -154,7 +163,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ -static inline u64 tk_clock_read(struct tk_read_base *tkr) +static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); @@ -203,7 +212,7 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) } } -static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) +static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; @@ -247,7 +256,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } -static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) +static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { u64 cycle_now, delta; @@ -344,7 +353,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; static inline u32 arch_gettimeoffset(void) { return 0; } #endif -static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta) +static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) { u64 nsec; @@ -355,7 +364,7 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta) return nsec + arch_gettimeoffset(); } -static inline u64 timekeeping_get_ns(struct tk_read_base *tkr) +static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { u64 delta; @@ -363,7 +372,7 @@ static inline u64 timekeeping_get_ns(struct tk_read_base *tkr) return timekeeping_delta_to_ns(tkr, delta); } -static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles) +static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { u64 delta; @@ -386,7 +395,8 @@ static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles) * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ -static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf) +static void update_fast_timekeeper(const struct tk_read_base *tkr, + struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; @@ -541,10 +551,10 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ -static void halt_fast_timekeeper(struct timekeeper *tk) +static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; - struct tk_read_base *tkr = &tk->tkr_mono; + const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); @@ -1269,7 +1279,7 @@ EXPORT_SYMBOL(do_settimeofday64); * * Adds or subtracts an offset value from the current time. */ -static int timekeeping_inject_offset(struct timespec64 *ts) +static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -1496,22 +1506,39 @@ void __weak read_persistent_clock64(struct timespec64 *ts64) } /** - * read_boot_clock64 - Return time of the system start. + * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset + * from the boot. * * Weak dummy function for arches that do not yet support it. - * Function to read the exact time the system has been started. - * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported. - * - * XXX - Do be sure to remove it once all arches implement it. + * wall_time - current time as returned by persistent clock + * boot_offset - offset that is defined as wall_time - boot_time + * The default function calculates offset based on the current value of + * local_clock(). This way architectures that support sched_clock() but don't + * support dedicated boot time clock will provide the best estimate of the + * boot time. */ -void __weak read_boot_clock64(struct timespec64 *ts) +void __weak __init +read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, + struct timespec64 *boot_offset) { - ts->tv_sec = 0; - ts->tv_nsec = 0; + read_persistent_clock64(wall_time); + *boot_offset = ns_to_timespec64(local_clock()); } -/* Flag for if timekeeping_resume() has injected sleeptime */ -static bool sleeptime_injected; +/* + * Flag reflecting whether timekeeping_resume() has injected sleeptime. + * + * The flag starts of false and is only set when a suspend reaches + * timekeeping_suspend(), timekeeping_resume() sets it to false when the + * timekeeper clocksource is not stopping across suspend and has been + * used to update sleep time. If the timekeeper clocksource has stopped + * then the flag stays true and is used by the RTC resume code to decide + * whether sleeptime must be injected and if so the flag gets false then. + * + * If a suspend fails before reaching timekeeping_resume() then the flag + * stays false and prevents erroneous sleeptime injection. + */ +static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; @@ -1521,28 +1548,29 @@ static bool persistent_clock_exists; */ void __init timekeeping_init(void) { + struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; - struct timespec64 now, boot, tmp; - - read_persistent_clock64(&now); - if (!timespec64_valid_strict(&now)) { - pr_warn("WARNING: Persistent clock returned invalid value!\n" - " Check your CMOS/BIOS settings.\n"); - now.tv_sec = 0; - now.tv_nsec = 0; - } else if (now.tv_sec || now.tv_nsec) - persistent_clock_exists = true; - read_boot_clock64(&boot); - if (!timespec64_valid_strict(&boot)) { - pr_warn("WARNING: Boot clock returned invalid value!\n" - " Check your CMOS/BIOS settings.\n"); - boot.tv_sec = 0; - boot.tv_nsec = 0; + read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); + if (timespec64_valid_strict(&wall_time) && + timespec64_to_ns(&wall_time) > 0) { + persistent_clock_exists = true; + } else if (timespec64_to_ns(&wall_time) != 0) { + pr_warn("Persistent clock returned invalid value"); + wall_time = (struct timespec64){0}; } + if (timespec64_compare(&wall_time, &boot_offset) < 0) + boot_offset = (struct timespec64){0}; + + /* + * We want set wall_to_mono, so the following is true: + * wall time + wall_to_mono = boot time + */ + wall_to_mono = timespec64_sub(boot_offset, wall_time); + raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); ntp_init(); @@ -1552,13 +1580,10 @@ void __init timekeeping_init(void) clock->enable(clock); tk_setup_internals(tk, clock); - tk_set_xtime(tk, &now); + tk_set_xtime(tk, &wall_time); tk->raw_sec = 0; - if (boot.tv_sec == 0 && boot.tv_nsec == 0) - boot = tk_xtime(tk); - set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec); - tk_set_wall_to_mono(tk, tmp); + tk_set_wall_to_mono(tk, wall_to_mono); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); @@ -1577,7 +1602,7 @@ static struct timespec64 timekeeping_suspend_time; * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, - struct timespec64 *delta) + const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING @@ -1610,7 +1635,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, */ bool timekeeping_rtc_skipresume(void) { - return sleeptime_injected; + return !suspend_timing_needed; } /** @@ -1638,7 +1663,7 @@ bool timekeeping_rtc_skipsuspend(void) * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ -void timekeeping_inject_sleeptime64(struct timespec64 *delta) +void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; @@ -1646,6 +1671,8 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta) raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); + suspend_timing_needed = false; + timekeeping_forward_now(tk); __timekeeping_inject_sleeptime(tk, delta); @@ -1669,9 +1696,9 @@ void timekeeping_resume(void) struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; - u64 cycle_now; + u64 cycle_now, nsec; + bool inject_sleeptime = false; - sleeptime_injected = false; read_persistent_clock64(&ts_new); clockevents_resume(); @@ -1693,22 +1720,19 @@ void timekeeping_resume(void) * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); - if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > tk->tkr_mono.cycle_last) { - u64 nsec, cyc_delta; - - cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, - tk->tkr_mono.mask); - nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift); + nsec = clocksource_stop_suspend_timing(clock, cycle_now); + if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); - sleeptime_injected = true; + inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); - sleeptime_injected = true; + inject_sleeptime = true; } - if (sleeptime_injected) + if (inject_sleeptime) { + suspend_timing_needed = false; __timekeeping_inject_sleeptime(tk, &ts_delta); + } /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; @@ -1732,6 +1756,8 @@ int timekeeping_suspend(void) unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; + struct clocksource *curr_clock; + u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); @@ -1743,11 +1769,22 @@ int timekeeping_suspend(void) if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; + suspend_timing_needed = true; + raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; + /* + * Since we've called forward_now, cycle_last stores the value + * just read from the current clocksource. Save this to potentially + * use in suspend timing. + */ + curr_clock = tk->tkr_mono.clock; + cycle_now = tk->tkr_mono.cycle_last; + clocksource_start_suspend_timing(curr_clock, cycle_now); + if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, @@ -2021,11 +2058,11 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, return offset; } -/** - * update_wall_time - Uses the current clocksource to increment the wall time - * +/* + * timekeeping_advance - Updates the timekeeper to the current time and + * current NTP tick length */ -void update_wall_time(void) +static void timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; @@ -2042,14 +2079,17 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; + + if (mode != TK_ADV_TICK) + goto out; #else offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); -#endif /* Check if there's really nothing to do */ - if (offset < real_tk->cycle_interval) + if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) goto out; +#endif /* Do some additional sanity checking */ timekeeping_check_update(tk, offset); @@ -2106,6 +2146,15 @@ out: } /** + * update_wall_time - Uses the current clocksource to increment the wall time + * + */ +void update_wall_time(void) +{ + timekeeping_advance(TK_ADV_TICK); +} + +/** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * @@ -2220,7 +2269,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ -static int timekeeping_validate_timex(struct timex *txc) +static int timekeeping_validate_timex(const struct timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ @@ -2310,7 +2359,7 @@ int do_adjtimex(struct timex *txc) return ret; } - getnstimeofday64(&ts); + ktime_get_real_ts64(&ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); @@ -2327,6 +2376,10 @@ int do_adjtimex(struct timex *txc) write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + /* Update the multiplier immediately if frequency was set directly */ + if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) + timekeeping_advance(TK_ADV_FREQ); + if (tai != orig_tai) clock_was_set(); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index 0754cadfa9e6..238e4be60229 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -70,7 +70,7 @@ static int __init tk_debug_sleep_time_init(void) } late_initcall(tk_debug_sleep_time_init); -void tk_debug_account_sleep_time(struct timespec64 *t) +void tk_debug_account_sleep_time(const struct timespec64 *t) { /* Cap bin index so we don't overflow the array */ int bin = min(fls(t->tv_sec), NUM_BINS-1); diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index cf5c0828ee31..bcbb52db2256 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -8,7 +8,7 @@ #include <linux/time.h> #ifdef CONFIG_DEBUG_FS -extern void tk_debug_account_sleep_time(struct timespec64 *t); +extern void tk_debug_account_sleep_time(const struct timespec64 *t); #else #define tk_debug_account_sleep_time(x) #endif diff --git a/kernel/time/timer.c b/kernel/time/timer.c index cc2d23e6ff61..fa49cd753dea 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -581,7 +581,7 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) * wheel: */ base->next_expiry = timer->expires; - wake_up_nohz_cpu(base->cpu); + wake_up_nohz_cpu(base->cpu); } static void @@ -1657,6 +1657,22 @@ static inline void __run_timers(struct timer_base *base) raw_spin_lock_irq(&base->lock); + /* + * timer_base::must_forward_clk must be cleared before running + * timers so that any timer functions that call mod_timer() will + * not try to forward the base. Idle tracking / clock forwarding + * logic is only used with BASE_STD timers. + * + * The must_forward_clk flag is cleared unconditionally also for + * the deferrable base. The deferrable base is not affected by idle + * tracking and never forwarded, so clearing the flag is a NOOP. + * + * The fact that the deferrable base is never forwarded can cause + * large variations in granularity for deferrable timers, but they + * can be deferred for long periods due to idle anyway. + */ + base->must_forward_clk = false; + while (time_after_eq(jiffies, base->clk)) { levels = collect_expired_timers(base, heads); @@ -1676,19 +1692,6 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - /* - * must_forward_clk must be cleared before running timers so that any - * timer functions that call mod_timer will not try to forward the - * base. idle trcking / clock forwarding logic is only used with - * BASE_STD timers. - * - * The deferrable base does not do idle tracking at all, so we do - * not forward it. This can result in very large variations in - * granularity for deferrable timers, but they can be deferred for - * long periods due to idle. - */ - base->must_forward_clk = false; - __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); diff --git a/kernel/torture.c b/kernel/torture.c index 3de1efbecd6a..1ac24a826589 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -20,6 +20,9 @@ * Author: Paul E. McKenney <paulmck@us.ibm.com> * Based on kernel/rcu/torture.c. */ + +#define pr_fmt(fmt) fmt + #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> @@ -53,7 +56,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>"); static char *torture_type; -static bool verbose; +static int verbose; /* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */ #define FULLSTOP_DONTSTOP 0 /* Normal operation. */ @@ -98,7 +101,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) return false; - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: offlining %d\n", torture_type, cpu); @@ -111,7 +114,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, "torture_onoff task: offline %d failed: errno %d\n", torture_type, cpu, ret); } else { - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: offlined %d\n", torture_type, cpu); @@ -147,7 +150,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) return false; - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: onlining %d\n", torture_type, cpu); @@ -160,7 +163,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, "torture_onoff task: online %d failed: errno %d\n", torture_type, cpu, ret); } else { - if (verbose) + if (verbose > 1) pr_alert("%s" TORTURE_FLAG "torture_onoff task: onlined %d\n", torture_type, cpu); @@ -647,7 +650,7 @@ static void torture_stutter_cleanup(void) * The runnable parameter points to a flag that controls whether or not * the test is currently runnable. If there is no such flag, pass in NULL. */ -bool torture_init_begin(char *ttype, bool v) +bool torture_init_begin(char *ttype, int v) { mutex_lock(&fullstop_mutex); if (torture_type != NULL) { diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index c4f0f2e4126e..9a27f146fa1c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -12,22 +12,22 @@ config NOP_TRACER config HAVE_FTRACE_NMI_ENTER bool help - See Documentation/trace/ftrace-design.txt + See Documentation/trace/ftrace-design.rst config HAVE_FUNCTION_TRACER bool help - See Documentation/trace/ftrace-design.txt + See Documentation/trace/ftrace-design.rst config HAVE_FUNCTION_GRAPH_TRACER bool help - See Documentation/trace/ftrace-design.txt + See Documentation/trace/ftrace-design.rst config HAVE_DYNAMIC_FTRACE bool help - See Documentation/trace/ftrace-design.txt + See Documentation/trace/ftrace-design.rst config HAVE_DYNAMIC_FTRACE_WITH_REGS bool @@ -35,12 +35,12 @@ config HAVE_DYNAMIC_FTRACE_WITH_REGS config HAVE_FTRACE_MCOUNT_RECORD bool help - See Documentation/trace/ftrace-design.txt + See Documentation/trace/ftrace-design.rst config HAVE_SYSCALL_TRACEPOINTS bool help - See Documentation/trace/ftrace-design.txt + See Documentation/trace/ftrace-design.rst config HAVE_FENTRY bool @@ -110,11 +110,7 @@ config GENERIC_TRACER # config TRACING_SUPPORT bool - # PPC32 has no irqflags tracing support, but it can use most of the - # tracers anyway, they were tested to build and work. Note that new - # exceptions to this list aren't welcomed, better implement the - # irqflags tracing for your architecture. - depends on TRACE_IRQFLAGS_SUPPORT || PPC32 + depends on TRACE_IRQFLAGS_SUPPORT depends on STACKTRACE_SUPPORT default y @@ -452,7 +448,7 @@ config KPROBE_EVENTS help This allows the user to add tracing events (similar to tracepoints) on the fly via the ftrace interface. See - Documentation/trace/kprobetrace.txt for more details. + Documentation/trace/kprobetrace.rst for more details. Those events can be inserted wherever kprobes can probe, and record various register and memory values. @@ -525,7 +521,7 @@ config FUNCTION_PROFILER in debugfs called function_profile_enabled which defaults to zero. When a 1 is echoed into this file profiling begins, and when a zero is entered, profiling stops. A "functions" file is created in - the trace_stats directory; this file shows the list of functions that + the trace_stat directory; this file shows the list of functions that have been hit and their counters. If in doubt, say N. @@ -579,7 +575,7 @@ config MMIOTRACE implementation and works via page faults. Tracing is disabled by default and can be enabled at run-time. - See Documentation/trace/mmiotrace.txt. + See Documentation/trace/mmiotrace.rst. If you are not helping to develop drivers, say N. config TRACING_MAP @@ -609,7 +605,7 @@ config HIST_TRIGGERS Inter-event tracing of quantities such as latencies is also supported using hist triggers under this option. - See Documentation/trace/histogram.txt. + See Documentation/trace/histogram.rst. If in doubt, say N. config MMIOTRACE_TEST diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 987d9a9ae283..b951aa1fac61 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -494,6 +494,9 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!buts->buf_size || !buts->buf_nr) return -EINVAL; + if (!blk_debugfs_root) + return -ENOENT; + strncpy(buts->name, name, BLKTRACE_BDEV_SIZE); buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0'; @@ -518,9 +521,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = -ENOENT; - if (!blk_debugfs_root) - goto err; - dir = debugfs_lookup(buts->name, blk_debugfs_root); if (!dir) bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 56ba0f2a01db..0ae6829804bc 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -14,12 +14,14 @@ #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/kprobes.h> +#include <linux/syscalls.h> #include <linux/error-injection.h> #include "trace_probe.h" #include "trace.h" u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); /** * trace_call_bpf - invoke BPF program @@ -474,8 +476,6 @@ BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; - if (unlikely(in_interrupt())) - return -EINVAL; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; @@ -564,6 +564,10 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_str_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; +#endif default: return NULL; } @@ -577,6 +581,8 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE @@ -664,6 +670,25 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack_tp, void *, tp_buff, void *, buf, u32, size, + u64, flags) +{ + struct pt_regs *regs = *(struct pt_regs **)tp_buff; + + return bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); +} + +static const struct bpf_func_proto bpf_get_stack_proto_tp = { + .func = bpf_get_stack_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -672,6 +697,8 @@ tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_tp; default: return tracing_func_proto(func_id, prog); } @@ -734,6 +761,8 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_tp; case BPF_FUNC_perf_prog_read_value: return &bpf_perf_prog_read_value_proto; default: @@ -744,7 +773,7 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) /* * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp * to avoid potential recursive reuse issue when/if tracepoints are added - * inside bpf_*_event_output and/or bpf_get_stack_id + * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack */ static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs); BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args, @@ -787,6 +816,26 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args, + void *, buf, u32, size, u64, flags) +{ + struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + + perf_fetch_caller_regs(regs); + return bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); +} + +static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { + .func = bpf_get_stack_raw_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -795,6 +844,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_raw_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_raw_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_raw_tp; default: return tracing_func_proto(func_id, prog); } @@ -833,8 +884,14 @@ static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type return false; if (type != BPF_READ) return false; - if (off % size != 0) - return false; + if (off % size != 0) { + if (sizeof(unsigned long) != 4) + return false; + if (size != 8) + return false; + if (off % size != 4) + return false; + } switch (off) { case bpf_ctx_range(struct bpf_perf_event_data, sample_period): @@ -959,6 +1016,8 @@ void perf_event_detach_bpf_prog(struct perf_event *event) old_array = event->tp_event->prog_array; ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array); + if (ret == -ENOENT) + goto unlock; if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { @@ -1117,3 +1176,50 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) mutex_unlock(&bpf_event_mutex); return err; } + +int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, + u32 *fd_type, const char **buf, + u64 *probe_offset, u64 *probe_addr) +{ + bool is_tracepoint, is_syscall_tp; + struct bpf_prog *prog; + int flags, err = 0; + + prog = event->prog; + if (!prog) + return -ENOENT; + + /* not supporting BPF_PROG_TYPE_PERF_EVENT yet */ + if (prog->type == BPF_PROG_TYPE_PERF_EVENT) + return -EOPNOTSUPP; + + *prog_id = prog->aux->id; + flags = event->tp_event->flags; + is_tracepoint = flags & TRACE_EVENT_FL_TRACEPOINT; + is_syscall_tp = is_syscall_trace_event(event->tp_event); + + if (is_tracepoint || is_syscall_tp) { + *buf = is_tracepoint ? event->tp_event->tp->name + : event->tp_event->name; + *fd_type = BPF_FD_TYPE_TRACEPOINT; + *probe_offset = 0x0; + *probe_addr = 0x0; + } else { + /* kprobe/uprobe */ + err = -EOPNOTSUPP; +#ifdef CONFIG_KPROBE_EVENTS + if (flags & TRACE_EVENT_FL_KPROBE) + err = bpf_get_kprobe_info(event, fd_type, buf, + probe_offset, probe_addr, + event->attr.type == PERF_TYPE_TRACEPOINT); +#endif +#ifdef CONFIG_UPROBE_EVENTS + if (flags & TRACE_EVENT_FL_UPROBE) + err = bpf_get_uprobe_info(event, fd_type, buf, + probe_offset, + event->attr.type == PERF_TYPE_TRACEPOINT); +#endif + } + + return err; +} diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8d83bcf9ef69..caf9cbf35816 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -192,17 +192,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, op->saved_func(ip, parent_ip, op, regs); } -/** - * clear_ftrace_function - reset the ftrace function - * - * This NULLs the ftrace function and in essence stops - * tracing. There may be lag - */ -void clear_ftrace_function(void) -{ - ftrace_trace_function = ftrace_stub; -} - static void ftrace_sync(struct work_struct *work) { /* @@ -728,7 +717,7 @@ static int ftrace_profile_init_cpu(int cpu) */ size = FTRACE_PROFILE_HASH_SIZE; - stat->hash = kzalloc(sizeof(struct hlist_head) * size, GFP_KERNEL); + stat->hash = kcalloc(size, sizeof(struct hlist_head), GFP_KERNEL); if (!stat->hash) return -ENOMEM; @@ -6689,7 +6678,7 @@ void ftrace_kill(void) { ftrace_disabled = 1; ftrace_enabled = 0; - clear_ftrace_function(); + ftrace_trace_function = ftrace_stub; } /** @@ -6830,9 +6819,10 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) struct task_struct *g, *t; for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) { - ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH - * sizeof(struct ftrace_ret_stack), - GFP_KERNEL); + ret_stack_list[i] = + kmalloc_array(FTRACE_RETFUNC_DEPTH, + sizeof(struct ftrace_ret_stack), + GFP_KERNEL); if (!ret_stack_list[i]) { start = 0; end = i; @@ -6904,9 +6894,9 @@ static int start_graph_tracing(void) struct ftrace_ret_stack **ret_stack_list; int ret, cpu; - ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE * - sizeof(struct ftrace_ret_stack *), - GFP_KERNEL); + ret_stack_list = kmalloc_array(FTRACE_RETSTACK_ALLOC_SIZE, + sizeof(struct ftrace_ret_stack *), + GFP_KERNEL); if (!ret_stack_list) return -ENOMEM; @@ -7088,9 +7078,10 @@ void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) ret_stack = per_cpu(idle_ret_stack, cpu); if (!ret_stack) { - ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH - * sizeof(struct ftrace_ret_stack), - GFP_KERNEL); + ret_stack = + kmalloc_array(FTRACE_RETFUNC_DEPTH, + sizeof(struct ftrace_ret_stack), + GFP_KERNEL); if (!ret_stack) return; per_cpu(idle_ret_stack, cpu) = ret_stack; @@ -7109,9 +7100,9 @@ void ftrace_graph_init_task(struct task_struct *t) if (ftrace_graph_active) { struct ftrace_ret_stack *ret_stack; - ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH - * sizeof(struct ftrace_ret_stack), - GFP_KERNEL); + ret_stack = kmalloc_array(FTRACE_RETFUNC_DEPTH, + sizeof(struct ftrace_ret_stack), + GFP_KERNEL); if (!ret_stack) return; graph_init_task(t, ret_stack); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c9cb9767d49b..0b0b688ea166 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -809,7 +809,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); * * You can see, it is legitimate for the previous pointer of * the head (or any page) not to point back to itself. But only - * temporarially. + * temporarily. */ #define RB_PAGE_NORMAL 0UL @@ -906,7 +906,7 @@ static void rb_list_head_clear(struct list_head *list) } /* - * rb_head_page_dactivate - clears head page ptr (for free list) + * rb_head_page_deactivate - clears head page ptr (for free list) */ static void rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer) @@ -1780,7 +1780,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, put_online_cpus(); } else { - /* Make sure this CPU has been intitialized */ + /* Make sure this CPU has been initialized */ if (!cpumask_test_cpu(cpu_id, buffer->cpumask)) goto out; @@ -2325,7 +2325,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, /* * If we need to add a timestamp, then we - * add it to the start of the resevered space. + * add it to the start of the reserved space. */ if (unlikely(info->add_timestamp)) { bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer); @@ -2681,7 +2681,7 @@ trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) * ring_buffer_nest_start - Allow to trace while nested * @buffer: The ring buffer to modify * - * The ring buffer has a safty mechanism to prevent recursion. + * The ring buffer has a safety mechanism to prevent recursion. * But there may be a case where a trace needs to be done while * tracing something else. In this case, calling this function * will allow this function to nest within a currently active @@ -2699,7 +2699,7 @@ void ring_buffer_nest_start(struct ring_buffer *buffer) preempt_disable_notrace(); cpu = raw_smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; - /* This is the shift value for the above recusive locking */ + /* This is the shift value for the above recursive locking */ cpu_buffer->nest += NESTED_BITS; } @@ -2718,7 +2718,7 @@ void ring_buffer_nest_end(struct ring_buffer *buffer) /* disabled by ring_buffer_nest_start() */ cpu = raw_smp_processor_id(); cpu_buffer = buffer->buffers[cpu]; - /* This is the shift value for the above recusive locking */ + /* This is the shift value for the above recursive locking */ cpu_buffer->nest -= NESTED_BITS; preempt_enable_notrace(); } @@ -2907,7 +2907,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, * @buffer: the ring buffer to reserve from * @length: the length of the data to reserve (excluding event header) * - * Returns a reseverd event on the ring buffer to copy directly to. + * Returns a reserved event on the ring buffer to copy directly to. * The user of this interface will need to get the body to write into * and can use the ring_buffer_event_data() interface. * @@ -3009,7 +3009,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, * This function lets the user discard an event in the ring buffer * and then that event will not be read later. * - * This function only works if it is called before the the item has been + * This function only works if it is called before the item has been * committed. It will try to free the event from the ring buffer * if another event has not been added behind it. * @@ -3227,6 +3227,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer) } /** + * ring_buffer_record_is_set_on - return true if the ring buffer is set writable + * @buffer: The ring buffer to see if write is set enabled + * + * Returns true if the ring buffer is set writable by ring_buffer_record_on(). + * Note that this does NOT mean it is in a writable state. + * + * It may return true when the ring buffer has been disabled by + * ring_buffer_record_disable(), as that is a temporary disabling of + * the ring buffer. + */ +int ring_buffer_record_is_set_on(struct ring_buffer *buffer) +{ + return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF); +} + +/** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. * @cpu: The CPU buffer to stop @@ -4127,7 +4143,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume); * through the buffer. Memory is allocated, buffer recording * is disabled, and the iterator pointer is returned to the caller. * - * Disabling buffer recordng prevents the reading from being + * Disabling buffer recording prevents the reading from being * corrupted. This is not a consuming read, so a producer is not * expected. * diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f106ad12f72f..176debd3481b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1360,8 +1360,6 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct ring_buffer *buf; - if (tr->stop_count) return; @@ -1375,9 +1373,13 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); - buf = tr->trace_buffer.buffer; - tr->trace_buffer.buffer = tr->max_buffer.buffer; - tr->max_buffer.buffer = buf; + /* Inherit the recordable setting from trace_buffer */ + if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer)) + ring_buffer_record_on(tr->max_buffer.buffer); + else + ring_buffer_record_off(tr->max_buffer.buffer); + + swap(tr->trace_buffer.buffer, tr->max_buffer.buffer); __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); @@ -1751,12 +1753,13 @@ static inline void set_cmdline(int idx, const char *cmdline) static int allocate_cmdlines_buffer(unsigned int val, struct saved_cmdlines_buffer *s) { - s->map_cmdline_to_pid = kmalloc(val * sizeof(*s->map_cmdline_to_pid), - GFP_KERNEL); + s->map_cmdline_to_pid = kmalloc_array(val, + sizeof(*s->map_cmdline_to_pid), + GFP_KERNEL); if (!s->map_cmdline_to_pid) return -ENOMEM; - s->saved_cmdlines = kmalloc(val * TASK_COMM_LEN, GFP_KERNEL); + s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL); if (!s->saved_cmdlines) { kfree(s->map_cmdline_to_pid); return -ENOMEM; @@ -2956,6 +2959,7 @@ out_nobuffer: } EXPORT_SYMBOL_GPL(trace_vbprintk); +__printf(3, 0) static int __trace_array_vprintk(struct ring_buffer *buffer, unsigned long ip, const char *fmt, va_list args) @@ -3010,12 +3014,14 @@ out_nobuffer: return len; } +__printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args); } +__printf(3, 0) int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...) { @@ -3031,6 +3037,7 @@ int trace_array_printk(struct trace_array *tr, return ret; } +__printf(3, 4) int trace_array_printk_buf(struct ring_buffer *buffer, unsigned long ip, const char *fmt, ...) { @@ -3046,6 +3053,7 @@ int trace_array_printk_buf(struct ring_buffer *buffer, return ret; } +__printf(2, 0) int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { return trace_array_vprintk(&global_trace, ip, fmt, args); @@ -3363,8 +3371,8 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m, print_event_info(buf, m); - seq_printf(m, "# TASK-PID CPU# %s TIMESTAMP FUNCTION\n", tgid ? "TGID " : ""); - seq_printf(m, "# | | | %s | |\n", tgid ? " | " : ""); + seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : ""); + seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); } static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m, @@ -3384,9 +3392,9 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file tgid ? tgid_space : space); seq_printf(m, "# %s||| / delay\n", tgid ? tgid_space : space); - seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n", + seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n", tgid ? " TGID " : space); - seq_printf(m, "# | | | %s|||| | |\n", + seq_printf(m, "# | | %s | |||| | |\n", tgid ? " | " : space); } @@ -4360,7 +4368,8 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) if (mask == TRACE_ITER_RECORD_TGID) { if (!tgid_map) - tgid_map = kzalloc((PID_MAX_DEFAULT + 1) * sizeof(*tgid_map), + tgid_map = kcalloc(PID_MAX_DEFAULT + 1, + sizeof(*tgid_map), GFP_KERNEL); if (!tgid_map) { tr->trace_flags &= ~TRACE_ITER_RECORD_TGID; @@ -4395,8 +4404,7 @@ static int trace_set_options(struct trace_array *tr, char *option) { char *cmp; int neg = 0; - int ret = -ENODEV; - int i; + int ret; size_t orig_len = strlen(option); cmp = strstrip(option); @@ -4408,16 +4416,12 @@ static int trace_set_options(struct trace_array *tr, char *option) mutex_lock(&trace_types_lock); - for (i = 0; trace_options[i]; i++) { - if (strcmp(cmp, trace_options[i]) == 0) { - ret = set_tracer_flag(tr, 1 << i, !neg); - break; - } - } - + ret = match_string(trace_options, -1, cmp); /* If no option could be set, test the specific tracer options */ - if (!trace_options[i]) + if (ret < 0) ret = set_tracer_option(tr, cmp, neg); + else + ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); @@ -5068,7 +5072,7 @@ trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, * where the head holds the module and length of array, and the * tail holds a pointer to the next list. */ - map_array = kmalloc(sizeof(*map_array) * (len + 2), GFP_KERNEL); + map_array = kmalloc_array(len + 2, sizeof(*map_array), GFP_KERNEL); if (!map_array) { pr_warn("Unable to allocate trace eval mapping\n"); return; @@ -6074,6 +6078,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, { struct trace_array *tr = filp->private_data; struct ring_buffer_event *event; + enum event_trigger_type tt = ETT_NONE; struct ring_buffer *buffer; struct print_entry *entry; unsigned long irq_flags; @@ -6122,6 +6127,12 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, written = cnt; len = cnt; + if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) { + /* do not add \n before testing triggers, but add \0 */ + entry->buf[cnt] = '\0'; + tt = event_triggers_call(tr->trace_marker_file, entry, event); + } + if (entry->buf[cnt - 1] != '\n') { entry->buf[cnt] = '\n'; entry->buf[cnt + 1] = '\0'; @@ -6130,6 +6141,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, __buffer_unlock_commit(buffer, event); + if (tt) + event_triggers_post_call(tr->trace_marker_file, tt); + if (written > 0) *fpos += written; @@ -7896,6 +7910,7 @@ static __init void create_trace_instances(struct dentry *d_tracer) static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) { + struct trace_event_file *file; int cpu; trace_create_file("available_tracers", 0444, d_tracer, @@ -7928,6 +7943,12 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("trace_marker", 0220, d_tracer, tr, &tracing_mark_fops); + file = __find_event_file(tr, "ftrace", "print"); + if (file && file->dir) + trace_create_file("trigger", 0644, file->dir, file, + &event_trigger_fops); + tr->trace_marker_file = file; + trace_create_file("trace_marker_raw", 0220, d_tracer, tr, &tracing_mark_raw_fops); @@ -8111,6 +8132,8 @@ static __init int tracer_init_tracefs(void) if (IS_ERR(d_tracer)) return 0; + event_trace_init(); + init_tracer_tracefs(&global_trace, d_tracer); ftrace_init_tracefs_toplevel(&global_trace, d_tracer); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 507954b4e058..f8f86231ad90 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -259,6 +259,7 @@ struct trace_array { struct trace_options *topts; struct list_head systems; struct list_head events; + struct trace_event_file *trace_marker_file; cpumask_var_t tracing_cpumask; /* only trace on set CPUs */ int ref; #ifdef CONFIG_FUNCTION_TRACER @@ -582,9 +583,7 @@ static __always_inline void trace_clear_recursion(int bit) static inline struct ring_buffer_iter * trace_buffer_iter(struct trace_iterator *iter, int cpu) { - if (iter->buffer_iter && iter->buffer_iter[cpu]) - return iter->buffer_iter[cpu]; - return NULL; + return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL; } int tracer_init(struct tracer *t, struct trace_array *tr); @@ -1334,7 +1333,7 @@ event_trigger_unlock_commit(struct trace_event_file *file, trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc); if (tt) - event_triggers_post_call(file, tt, entry, event); + event_triggers_post_call(file, tt); } /** @@ -1367,7 +1366,7 @@ event_trigger_unlock_commit_regs(struct trace_event_file *file, irq_flags, pc, regs); if (tt) - event_triggers_post_call(file, tt, entry, event); + event_triggers_post_call(file, tt); } #define FILTER_PRED_INVALID ((unsigned short)-1) @@ -1451,9 +1450,13 @@ trace_find_event_field(struct trace_event_call *call, char *name); extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); +extern int event_trace_init(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); +extern struct trace_event_file *__find_event_file(struct trace_array *tr, + const char *system, + const char *event); extern struct trace_event_file *find_event_file(struct trace_array *tr, const char *system, const char *event); diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e3a658bac10f..1d67464ed95e 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -230,7 +230,7 @@ FTRACE_ENTRY(bprint, bprint_entry, FILTER_OTHER ); -FTRACE_ENTRY(print, print_entry, +FTRACE_ENTRY_REG(print, print_entry, TRACE_PRINT, @@ -242,7 +242,9 @@ FTRACE_ENTRY(print, print_entry, F_printk("%ps: %s", (void *)__entry->ip, __entry->buf), - FILTER_OTHER + FILTER_OTHER, + + ftrace_event_register ); FTRACE_ENTRY(raw_data, raw_data_entry, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 05c7172c6667..14ff4ff3caab 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2007,16 +2007,18 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) return -1; } } - trace_create_file("filter", 0644, file->dir, file, - &ftrace_event_filter_fops); /* * Only event directories that can be enabled should have - * triggers. + * triggers or filters. */ - if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) + if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) { + trace_create_file("filter", 0644, file->dir, file, + &ftrace_event_filter_fops); + trace_create_file("trigger", 0644, file->dir, file, &event_trigger_fops); + } #ifdef CONFIG_HIST_TRIGGERS trace_create_file("hist", 0444, file->dir, file, @@ -2473,8 +2475,9 @@ __trace_add_event_dirs(struct trace_array *tr) } } +/* Returns any file that matches the system and event */ struct trace_event_file * -find_event_file(struct trace_array *tr, const char *system, const char *event) +__find_event_file(struct trace_array *tr, const char *system, const char *event) { struct trace_event_file *file; struct trace_event_call *call; @@ -2485,10 +2488,7 @@ find_event_file(struct trace_array *tr, const char *system, const char *event) call = file->event_call; name = trace_event_name(call); - if (!name || !call->class || !call->class->reg) - continue; - - if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + if (!name || !call->class) continue; if (strcmp(event, name) == 0 && @@ -2498,6 +2498,20 @@ find_event_file(struct trace_array *tr, const char *system, const char *event) return NULL; } +/* Returns valid trace event files that match system and event */ +struct trace_event_file * +find_event_file(struct trace_array *tr, const char *system, const char *event) +{ + struct trace_event_file *file; + + file = __find_event_file(tr, system, event); + if (!file || !file->event_call->class->reg || + file->event_call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) + return NULL; + + return file; +} + #ifdef CONFIG_DYNAMIC_FTRACE /* Avoid typos */ @@ -3132,7 +3146,7 @@ static __init int event_trace_enable_again(void) early_initcall(event_trace_enable_again); -static __init int event_trace_init(void) +__init int event_trace_init(void) { struct trace_array *tr; struct dentry *d_tracer; @@ -3177,8 +3191,6 @@ void __init trace_event_init(void) event_trace_enable(); } -fs_initcall(event_trace_init); - #ifdef CONFIG_FTRACE_STARTUP_TEST static DEFINE_SPINLOCK(test_spinlock); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 7d306b74230f..893a206bcba4 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -78,7 +78,8 @@ static const char * ops[] = { OPS }; C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \ C(INVALID_FILTER, "Meaningless filter expression"), \ C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \ - C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), + C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \ + C(NO_FILTER, "No filter found"), #undef C #define C(a, b) FILT_ERR_##a @@ -436,15 +437,15 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, nr_preds += 2; /* For TRUE and FALSE */ - op_stack = kmalloc(sizeof(*op_stack) * nr_parens, GFP_KERNEL); + op_stack = kmalloc_array(nr_parens, sizeof(*op_stack), GFP_KERNEL); if (!op_stack) return ERR_PTR(-ENOMEM); - prog_stack = kmalloc(sizeof(*prog_stack) * nr_preds, GFP_KERNEL); + prog_stack = kmalloc_array(nr_preds, sizeof(*prog_stack), GFP_KERNEL); if (!prog_stack) { parse_error(pe, -ENOMEM, 0); goto out_free; } - inverts = kmalloc(sizeof(*inverts) * nr_preds, GFP_KERNEL); + inverts = kmalloc_array(nr_preds, sizeof(*inverts), GFP_KERNEL); if (!inverts) { parse_error(pe, -ENOMEM, 0); goto out_free; @@ -550,6 +551,13 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, goto out_free; } + if (!N) { + /* No program? */ + ret = -EINVAL; + parse_error(pe, FILT_ERR_NO_FILTER, ptr - str); + goto out_free; + } + prog[N].pred = NULL; /* #13 */ prog[N].target = 1; /* TRUE */ prog[N+1].pred = NULL; @@ -750,31 +758,32 @@ static int filter_pred_none(struct filter_pred *pred, void *event) * * Note: * - @str might not be NULL-terminated if it's of type DYN_STRING - * or STATIC_STRING + * or STATIC_STRING, unless @len is zero. */ static int regex_match_full(char *str, struct regex *r, int len) { - if (strncmp(str, r->pattern, len) == 0) - return 1; - return 0; + /* len of zero means str is dynamic and ends with '\0' */ + if (!len) + return strcmp(str, r->pattern) == 0; + + return strncmp(str, r->pattern, len) == 0; } static int regex_match_front(char *str, struct regex *r, int len) { - if (len < r->len) + if (len && len < r->len) return 0; - if (strncmp(str, r->pattern, r->len) == 0) - return 1; - return 0; + return strncmp(str, r->pattern, r->len) == 0; } static int regex_match_middle(char *str, struct regex *r, int len) { - if (strnstr(str, r->pattern, len)) - return 1; - return 0; + if (!len) + return strstr(str, r->pattern) != NULL; + + return strnstr(str, r->pattern, len) != NULL; } static int regex_match_end(char *str, struct regex *r, int len) @@ -1692,6 +1701,7 @@ static void create_filter_finish(struct filter_parse_error *pe) * @filter_str: filter string * @set_str: remember @filter_str and enable detailed error in filter * @filterp: out param for created filter (always updated on return) + * Must be a pointer that references a NULL pointer. * * Creates a filter for @call with @filter_str. If @set_str is %true, * @filter_str is copied and recorded in the new filter. @@ -1709,6 +1719,10 @@ static int create_filter(struct trace_event_call *call, struct filter_parse_error *pe = NULL; int err; + /* filterp must point to NULL */ + if (WARN_ON(*filterp)) + *filterp = NULL; + err = create_filter_start(filter_string, set_str, &pe, filterp); if (err) return err; diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index b9061ed59bbd..aae18af94c94 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -393,7 +393,7 @@ static void hist_err_event(char *str, char *system, char *event, char *var) else if (system) snprintf(err, MAX_FILTER_STR_VAL, "%s.%s", system, event); else - strncpy(err, var, MAX_FILTER_STR_VAL); + strscpy(err, var, MAX_FILTER_STR_VAL); hist_err(str, err); } @@ -2865,7 +2865,7 @@ static struct trace_event_file *event_file(struct trace_array *tr, { struct trace_event_file *file; - file = find_event_file(tr, system, event_name); + file = __find_event_file(tr, system, event_name); if (!file) return ERR_PTR(-EINVAL); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 8b5bdcf64871..5dea177cef53 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -97,7 +97,6 @@ EXPORT_SYMBOL_GPL(event_triggers_call); * event_triggers_post_call - Call 'post_triggers' for a trace event * @file: The trace_event_file associated with the event * @tt: enum event_trigger_type containing a set bit for each trigger to invoke - * @rec: The trace entry for the event * * For each trigger associated with an event, invoke the trigger * function registered with the associated trigger command, if the @@ -108,8 +107,7 @@ EXPORT_SYMBOL_GPL(event_triggers_call); */ void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt, - void *rec, struct ring_buffer_event *event) + enum event_trigger_type tt) { struct event_trigger_data *data; @@ -117,7 +115,7 @@ event_triggers_post_call(struct trace_event_file *file, if (data->paused) continue; if (data->cmd_ops->trigger_type & tt) - data->ops->func(data, rec, event); + data->ops->func(data, NULL, NULL); } } EXPORT_SYMBOL_GPL(event_triggers_post_call); @@ -681,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops, goto out_free; out_reg: + /* Up the trigger_data count to make sure reg doesn't free it on failure */ + event_trigger_init(trigger_ops, trigger_data); ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); /* * The above returns on success the # of functions enabled, @@ -688,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops, * Consider no functions a failure too. */ if (!ret) { + cmd_ops->unreg(glob, trigger_ops, trigger_data, file); ret = -ENOENT; - goto out_free; - } else if (ret < 0) - goto out_free; - ret = 0; + } else if (ret > 0) + ret = 0; + + /* Down the counter of trigger_data or free it if not used anymore */ + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1418,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out; } + /* Up the trigger_data count to make sure nothing frees it on failure */ + event_trigger_init(trigger_ops, trigger_data); + if (trigger) { number = strsep(&trigger, ":"); @@ -1468,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out_disable; /* Just return zero, not the number of enabled functions */ ret = 0; + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1478,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, out_free: if (cmd_ops->set_filter) cmd_ops->set_filter(NULL, trigger_data, NULL); - kfree(trigger_data); + event_trigger_free(trigger_ops, trigger_data); kfree(enable_data); goto out; } diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 548e62eb5c46..45630a76ed3a 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -14,6 +14,13 @@ #include "trace_output.h" +/* Stub function for events with triggers */ +static int ftrace_event_register(struct trace_event_call *call, + enum trace_reg type, void *data) +{ + return 0; +} + #undef TRACE_SYSTEM #define TRACE_SYSTEM ftrace @@ -117,7 +124,7 @@ static void __always_unused ____ftrace_check_##name(void) \ #undef __dynamic_array #define __dynamic_array(type, item) \ - ret = trace_define_field(event_call, #type, #item, \ + ret = trace_define_field(event_call, #type "[]", #item, \ offsetof(typeof(field), item), \ 0, is_signed_type(type), filter_type);\ if (ret) \ diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 23c0b0cb5fb9..169b3c44ee97 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -831,6 +831,7 @@ print_graph_entry_leaf(struct trace_iterator *iter, struct ftrace_graph_ret *graph_ret; struct ftrace_graph_ent *call; unsigned long long duration; + int cpu = iter->cpu; int i; graph_ret = &ret_entry->ret; @@ -839,7 +840,6 @@ print_graph_entry_leaf(struct trace_iterator *iter, if (data) { struct fgraph_cpu_data *cpu_data; - int cpu = iter->cpu; cpu_data = per_cpu_ptr(data->cpu_data, cpu); @@ -869,6 +869,9 @@ print_graph_entry_leaf(struct trace_iterator *iter, trace_seq_printf(s, "%ps();\n", (void *)call->func); + print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET, + cpu, iter->ent->pid, flags); + return trace_handle_return(s); } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 02aed76e0978..e9d99463e5df 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event, static int enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) { + struct event_file_link *link = NULL; int ret = 0; if (file) { - struct event_file_link *link; - link = kmalloc(sizeof(*link), GFP_KERNEL); if (!link) { ret = -ENOMEM; @@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) else ret = enable_kprobe(&tk->rp.kp); } + + if (ret) { + if (file) { + /* Notice the if is true on not WARN() */ + if (!WARN_ON_ONCE(!link)) + list_del_rcu(&link->list); + kfree(link); + tk->tp.flags &= ~TP_FLAG_TRACE; + } else { + tk->tp.flags &= ~TP_FLAG_PROFILE; + } + } out: return ret; } @@ -1217,16 +1228,11 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) /* * We need to check and see if we modified the pc of the - * pt_regs, and if so clear the kprobe and return 1 so that we - * don't do the single stepping. - * The ftrace kprobe handler leaves it up to us to re-enable - * preemption here before returning if we've modified the ip. + * pt_regs, and if so return 1 so that we don't do the + * single stepping. */ - if (orig_ip != instruction_pointer(regs)) { - reset_current_kprobe(); - preempt_enable_no_resched(); + if (orig_ip != instruction_pointer(regs)) return 1; - } if (!ret) return 0; } @@ -1287,6 +1293,35 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, head, NULL); } NOKPROBE_SYMBOL(kretprobe_perf_func); + +int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, + const char **symbol, u64 *probe_offset, + u64 *probe_addr, bool perf_type_tracepoint) +{ + const char *pevent = trace_event_name(event->tp_event); + const char *group = event->tp_event->class->system; + struct trace_kprobe *tk; + + if (perf_type_tracepoint) + tk = find_trace_kprobe(pevent, group); + else + tk = event->tp_event->data; + if (!tk) + return -EINVAL; + + *fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE + : BPF_FD_TYPE_KPROBE; + if (tk->symbol) { + *symbol = tk->symbol; + *probe_offset = tk->rp.kp.offset; + *probe_addr = 0; + } else { + *symbol = NULL; + *probe_offset = 0; + *probe_addr = (unsigned long)tk->rp.kp.addr; + } + return 0; +} #endif /* CONFIG_PERF_EVENTS */ /* @@ -1451,8 +1486,10 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, } ret = __register_trace_kprobe(tk); - if (ret < 0) + if (ret < 0) { + kfree(tk->tp.call.print_fmt); goto error; + } return &tk->tp.call; error: @@ -1472,6 +1509,8 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call) } __unregister_trace_kprobe(tk); + + kfree(tk->tp.call.print_fmt); free_trace_kprobe(tk); } #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 90db994ac900..1c8e30fda46a 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -594,8 +594,7 @@ int trace_print_context(struct trace_iterator *iter) trace_find_cmdline(entry->pid, comm); - trace_seq_printf(s, "%16s-%-5d [%03d] ", - comm, entry->pid, iter->cpu); + trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); if (tr->trace_flags & TRACE_ITER_RECORD_TGID) { unsigned int tgid = trace_find_tgid(entry->pid); @@ -606,6 +605,8 @@ int trace_print_context(struct trace_iterator *iter) trace_seq_printf(s, "(%5d) ", tgid); } + trace_seq_printf(s, "[%03d] ", iter->cpu); + if (tr->trace_flags & TRACE_ITER_IRQ_INFO) trace_print_lat_fmt(s, entry); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index ac892878dbe6..bf89a51e740d 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1161,6 +1161,28 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, { __uprobe_perf_func(tu, func, regs, ucb, dsize); } + +int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, + const char **filename, u64 *probe_offset, + bool perf_type_tracepoint) +{ + const char *pevent = trace_event_name(event->tp_event); + const char *group = event->tp_event->class->system; + struct trace_uprobe *tu; + + if (perf_type_tracepoint) + tu = find_probe_event(pevent, group); + else + tu = event->tp_event->data; + if (!tu) + return -EINVAL; + + *fd_type = is_ret_probe(tu) ? BPF_FD_TYPE_URETPROBE + : BPF_FD_TYPE_UPROBE; + *filename = tu->filename; + *probe_offset = tu->offset; + return 0; +} #endif /* CONFIG_PERF_EVENTS */ static int diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 5cadb1b8b5fe..752d8042bad4 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -1075,7 +1075,7 @@ int tracing_map_sort_entries(struct tracing_map *map, struct tracing_map_sort_entry *sort_entry, **entries; int i, n_entries, ret; - entries = vmalloc(map->max_elts * sizeof(sort_entry)); + entries = vmalloc(array_size(sizeof(sort_entry), map->max_elts)); if (!entries) return -ENOMEM; diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 1e37da2e0c25..6dc6356c3327 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -257,7 +257,7 @@ static int tracepoint_remove_func(struct tracepoint *tp, } /** - * tracepoint_probe_register - Connect a probe to a tracepoint + * tracepoint_probe_register_prio - Connect a probe to a tracepoint with priority * @tp: tracepoint * @probe: probe handler * @data: tracepoint data @@ -290,7 +290,6 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_register_prio); * @tp: tracepoint * @probe: probe handler * @data: tracepoint data - * @prio: priority of this function over other registered functions * * Returns 0 if ok, error value on error. * Note: if @tp is within a module, the caller is responsible for diff --git a/kernel/umh.c b/kernel/umh.c index f76b3ff876cf..c449858946af 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -25,6 +25,8 @@ #include <linux/ptrace.h> #include <linux/async.h> #include <linux/uaccess.h> +#include <linux/shmem_fs.h> +#include <linux/pipe_fs_i.h> #include <trace/events/module.h> @@ -97,9 +99,14 @@ static int call_usermodehelper_exec_async(void *data) commit_creds(new); - retval = do_execve(getname_kernel(sub_info->path), - (const char __user *const __user *)sub_info->argv, - (const char __user *const __user *)sub_info->envp); + sub_info->pid = task_pid_nr(current); + if (sub_info->file) + retval = do_execve_file(sub_info->file, + sub_info->argv, sub_info->envp); + else + retval = do_execve(getname_kernel(sub_info->path), + (const char __user *const __user *)sub_info->argv, + (const char __user *const __user *)sub_info->envp); out: sub_info->retval = retval; /* @@ -393,6 +400,117 @@ struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv, } EXPORT_SYMBOL(call_usermodehelper_setup); +struct subprocess_info *call_usermodehelper_setup_file(struct file *file, + int (*init)(struct subprocess_info *info, struct cred *new), + void (*cleanup)(struct subprocess_info *info), void *data) +{ + struct subprocess_info *sub_info; + + sub_info = kzalloc(sizeof(struct subprocess_info), GFP_KERNEL); + if (!sub_info) + return NULL; + + INIT_WORK(&sub_info->work, call_usermodehelper_exec_work); + sub_info->path = "none"; + sub_info->file = file; + sub_info->init = init; + sub_info->cleanup = cleanup; + sub_info->data = data; + return sub_info; +} + +static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) +{ + struct umh_info *umh_info = info->data; + struct file *from_umh[2]; + struct file *to_umh[2]; + int err; + + /* create pipe to send data to umh */ + err = create_pipe_files(to_umh, 0); + if (err) + return err; + err = replace_fd(0, to_umh[0], 0); + fput(to_umh[0]); + if (err < 0) { + fput(to_umh[1]); + return err; + } + + /* create pipe to receive data from umh */ + err = create_pipe_files(from_umh, 0); + if (err) { + fput(to_umh[1]); + replace_fd(0, NULL, 0); + return err; + } + err = replace_fd(1, from_umh[1], 0); + fput(from_umh[1]); + if (err < 0) { + fput(to_umh[1]); + replace_fd(0, NULL, 0); + fput(from_umh[0]); + return err; + } + + umh_info->pipe_to_umh = to_umh[1]; + umh_info->pipe_from_umh = from_umh[0]; + return 0; +} + +static void umh_save_pid(struct subprocess_info *info) +{ + struct umh_info *umh_info = info->data; + + umh_info->pid = info->pid; +} + +/** + * fork_usermode_blob - fork a blob of bytes as a usermode process + * @data: a blob of bytes that can be do_execv-ed as a file + * @len: length of the blob + * @info: information about usermode process (shouldn't be NULL) + * + * Returns either negative error or zero which indicates success + * in executing a blob of bytes as a usermode process. In such + * case 'struct umh_info *info' is populated with two pipes + * and a pid of the process. The caller is responsible for health + * check of the user process, killing it via pid, and closing the + * pipes when user process is no longer needed. + */ +int fork_usermode_blob(void *data, size_t len, struct umh_info *info) +{ + struct subprocess_info *sub_info; + struct file *file; + ssize_t written; + loff_t pos = 0; + int err; + + file = shmem_kernel_file_setup("", len, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + + written = kernel_write(file, data, len, &pos); + if (written != len) { + err = written; + if (err >= 0) + err = -ENOMEM; + goto out; + } + + err = -ENOMEM; + sub_info = call_usermodehelper_setup_file(file, umh_pipe_setup, + umh_save_pid, info); + if (!sub_info) + goto out; + + err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); +out: + fput(file); + return err; +} +EXPORT_SYMBOL_GPL(fork_usermode_blob); + /** * call_usermodehelper_exec - start a usermode application * @sub_info: information about the subprocessa diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 246d4d4ce5c7..c3d7583fcd21 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -764,8 +764,9 @@ static int insert_extent(struct uid_gid_map *map, struct uid_gid_extent *extent) struct uid_gid_extent *forward; /* Allocate memory for 340 mappings. */ - forward = kmalloc(sizeof(struct uid_gid_extent) * - UID_GID_MAP_MAX_EXTENTS, GFP_KERNEL); + forward = kmalloc_array(UID_GID_MAP_MAX_EXTENTS, + sizeof(struct uid_gid_extent), + GFP_KERNEL); if (!forward) return -ENOMEM; @@ -1235,6 +1236,7 @@ bool current_in_userns(const struct user_namespace *target_ns) { return in_userns(target_ns, current_user_ns()); } +EXPORT_SYMBOL(current_in_userns); static inline struct user_namespace *to_user_ns(struct ns_common *ns) { diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 576d18045811..5470dce212c0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -18,18 +18,14 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/sysctl.h> -#include <linux/smpboot.h> -#include <linux/sched/rt.h> -#include <uapi/linux/sched/types.h> #include <linux/tick.h> -#include <linux/workqueue.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> +#include <linux/stop_machine.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h> -#include <linux/kthread.h> static DEFINE_MUTEX(watchdog_mutex); @@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void) unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; -static bool softlockup_threads_initialized __read_mostly; +static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); -static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); @@ -335,6 +330,27 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } +static DEFINE_PER_CPU(struct completion, softlockup_completion); +static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); + +/* + * The watchdog thread function - touches the timestamp. + * + * It only runs once every sample_period seconds (4 seconds by + * default) to reset the softlockup timestamp. If this gets delayed + * for more than 2*watchdog_thresh seconds then the debug-printout + * triggers in watchdog_timer_fn(). + */ +static int softlockup_fn(void *data) +{ + __this_cpu_write(soft_lockup_hrtimer_cnt, + __this_cpu_read(hrtimer_interrupts)); + __touch_watchdog(); + complete(this_cpu_ptr(&softlockup_completion)); + + return 0; +} + /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -350,7 +366,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) watchdog_interrupt_count(); /* kick the softlockup detector */ - wake_up_process(__this_cpu_read(softlockup_watchdog)); + if (completion_done(this_cpu_ptr(&softlockup_completion))) { + reinit_completion(this_cpu_ptr(&softlockup_completion)); + stop_one_cpu_nowait(smp_processor_id(), + softlockup_fn, NULL, + this_cpu_ptr(&softlockup_stop_work)); + } /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); @@ -448,16 +469,15 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; } -static void watchdog_set_prio(unsigned int policy, unsigned int prio) -{ - struct sched_param param = { .sched_priority = prio }; - - sched_setscheduler(current, policy, ¶m); -} - static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); + struct completion *done = this_cpu_ptr(&softlockup_completion); + + WARN_ON_ONCE(cpu != smp_processor_id()); + + init_completion(done); + complete(done); /* * Start the timer first to prevent the NMI watchdog triggering @@ -473,15 +493,14 @@ static void watchdog_enable(unsigned int cpu) /* Enable the perf event */ if (watchdog_enabled & NMI_WATCHDOG_ENABLED) watchdog_nmi_enable(cpu); - - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - watchdog_set_prio(SCHED_NORMAL, 0); + WARN_ON_ONCE(cpu != smp_processor_id()); + /* * Disable the perf event first. That prevents that a large delay * between disabling the timer and disabling the perf event causes @@ -489,79 +508,66 @@ static void watchdog_disable(unsigned int cpu) */ watchdog_nmi_disable(cpu); hrtimer_cancel(hrtimer); + wait_for_completion(this_cpu_ptr(&softlockup_completion)); } -static void watchdog_cleanup(unsigned int cpu, bool online) +static int softlockup_stop_fn(void *data) { - watchdog_disable(cpu); + watchdog_disable(smp_processor_id()); + return 0; } -static int watchdog_should_run(unsigned int cpu) +static void softlockup_stop_all(void) { - return __this_cpu_read(hrtimer_interrupts) != - __this_cpu_read(soft_lockup_hrtimer_cnt); + int cpu; + + if (!softlockup_initialized) + return; + + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false); + + cpumask_clear(&watchdog_allowed_mask); } -/* - * The watchdog thread function - touches the timestamp. - * - * It only runs once every sample_period seconds (4 seconds by - * default) to reset the softlockup timestamp. If this gets delayed - * for more than 2*watchdog_thresh seconds then the debug-printout - * triggers in watchdog_timer_fn(). - */ -static void watchdog(unsigned int cpu) +static int softlockup_start_fn(void *data) { - __this_cpu_write(soft_lockup_hrtimer_cnt, - __this_cpu_read(hrtimer_interrupts)); - __touch_watchdog(); + watchdog_enable(smp_processor_id()); + return 0; } -static struct smp_hotplug_thread watchdog_threads = { - .store = &softlockup_watchdog, - .thread_should_run = watchdog_should_run, - .thread_fn = watchdog, - .thread_comm = "watchdog/%u", - .setup = watchdog_enable, - .cleanup = watchdog_cleanup, - .park = watchdog_disable, - .unpark = watchdog_enable, -}; - -static void softlockup_update_smpboot_threads(void) +static void softlockup_start_all(void) { - lockdep_assert_held(&watchdog_mutex); - - if (!softlockup_threads_initialized) - return; + int cpu; - smpboot_update_cpumask_percpu_thread(&watchdog_threads, - &watchdog_allowed_mask); + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + for_each_cpu(cpu, &watchdog_allowed_mask) + smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false); } -/* Temporarily park all watchdog threads */ -static void softlockup_park_all_threads(void) +int lockup_detector_online_cpu(unsigned int cpu) { - cpumask_clear(&watchdog_allowed_mask); - softlockup_update_smpboot_threads(); + watchdog_enable(cpu); + return 0; } -/* Unpark enabled threads */ -static void softlockup_unpark_threads(void) +int lockup_detector_offline_cpu(unsigned int cpu) { - cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); - softlockup_update_smpboot_threads(); + watchdog_disable(cpu); + return 0; } static void lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); - softlockup_park_all_threads(); + + softlockup_stop_all(); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) - softlockup_unpark_threads(); + softlockup_start_all(); + watchdog_nmi_start(); cpus_read_unlock(); /* @@ -580,8 +586,6 @@ static void lockup_detector_reconfigure(void) */ static __init void lockup_detector_setup(void) { - int ret; - /* * If sysctl is off and watchdog got disabled on the command line, * nothing to do here. @@ -592,24 +596,13 @@ static __init void lockup_detector_setup(void) !(watchdog_enabled && watchdog_thresh)) return; - ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_allowed_mask); - if (ret) { - pr_err("Failed to initialize soft lockup detector threads\n"); - return; - } - mutex_lock(&watchdog_mutex); - softlockup_threads_initialized = true; lockup_detector_reconfigure(); + softlockup_initialized = true; mutex_unlock(&watchdog_mutex); } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ -static inline int watchdog_park_threads(void) { return 0; } -static inline void watchdog_unpark_threads(void) { } -static inline int watchdog_enable_all_cpus(void) { return 0; } -static inline void watchdog_disable_all_cpus(void) { } static void lockup_detector_reconfigure(void) { cpus_read_lock(); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index e449a23e9d59..1f7020d65d0a 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -175,8 +175,8 @@ static int hardlockup_detector_event_create(void) evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); if (IS_ERR(evt)) { - pr_info("Perf event create on CPU %d failed with %ld\n", cpu, - PTR_ERR(evt)); + pr_debug("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); return PTR_ERR(evt); } this_cpu_write(watchdog_ev, evt); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 7ea75529eabb..78b192071ef7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3714,8 +3714,7 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, lockdep_assert_held(&wq_pool_mutex); - ctx = kzalloc(sizeof(*ctx) + nr_node_ids * sizeof(ctx->pwq_tbl[0]), - GFP_KERNEL); + ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(GFP_KERNEL); tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL); @@ -4363,6 +4362,7 @@ void set_worker_desc(const char *fmt, ...) va_end(args); } } +EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description @@ -5638,7 +5638,7 @@ static void __init wq_numa_init(void) * available. Build one from cpu_to_node() which should have been * fully initialized by now. */ - tbl = kzalloc(nr_node_ids * sizeof(tbl[0]), GFP_KERNEL); + tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL); BUG_ON(!tbl); for_each_node(node) |